2025 Spring UVa CS Generative AI Seminar Lectures Organized by Given Order

No. Title
1 Introduction
2 LLM basics - emergent ability and GenAI platform
3 more LLM basics - a survey
4 Survey - BioScience LLMs
5 Survey - FMs in healthcare
6 Survey - FMs in Robotics
7 advanced LLM - for code reasoning
8 advanced LLM - Math reasoning
9 Platform - Prompting Engineering tools / Prompt Compression
10 Platform - Context construction via RAG and Agent
11 Platform - Agent Tooling
12 Platform - More agent related
13 Platform - Model Jailbreaking / Safeguarding
14 Platform - VLM Jailbreaking / Probing
15 Platform - Model Customization - instruction tuning / LoRA
16 Platform - Model Serving + PPO
17 Extra - BioLLM
18 Extra readings - Agent Guardrailing
19 Agent - In Healthcare
20 Platform - long context vs RAG + Hallucination
21 Agent - Planning / World Model
22 Agent Safety / More Autonomous Agents
23 Agent - multiagent collaboration
24 Agent Efficiency - Model Serving + PPO
25 Project discussion session!
26 multimodal FMs - video / audio
27 Small foundation models
28 Model Interpretibility for FM
29 Inference test time scaling law
30 Model serving - Efficiency + PPO
31 students project presentations
---- ----

1.Introduction

BasicLLM

Summary of Post :

Readings:

Basics of ML and DL:

Basics of NLP

  • URL
  • Typical NLP tasks / Challenges / Pipeline
  • f() on natural language
    • Before Deep NLP (Pre 2012) • (BOW / LSI / Topic Modeling LDA )
    • Word2Vec (2013-2016) • (GloVe/ FastText)
    • Recurrent NN (2014-2016) • LSTM
    • Seq2Seq
    • Attention
    • Self-Attention (2016 – now )
    • Transformer (attention only Seq2Seq)
    • BERT / RoBERTa/ XLNet/ GPT / …
  • A good code walk through on transformer at URL


Please click each post's URL shown below to check out its full contents.

2.LLM basics - emergent ability and GenAI platform

BasicLLM

Summary of Post :

Readings:

Emergent Abilities of Large Language Models

  • URL
  • “an ability to be emergent if it is not present in smaller models but is present in larger models. Thus, emergent abilities cannot be predicted simply by extrapolating the performance of smaller models.”

Language Models are Few-Shot Learners

  • URL
  • “GPT-3, 175B autoregerssive LLM; show that scaling up language models greatly improves task-agnostic, few-shot performance, sometimes even reaching competitiveness with prior state-of-the-art fine-tuning approaches.”

GenAI Platform

Extra Readings:

A survey of Generative AI Applications

  • https://arxiv.org/abs/2306.02781
  • Generative AI has experienced remarkable growth in recent years, leading to a wide array of applications across diverse domains. In this paper, we present a comprehensive survey of more than 350 generative AI applications, providing a structured taxonomy and concise descriptions of various unimodal and even multimodal generative AIs. The survey is organized into sections, covering a wide range of unimodal generative AI applications such as text, images, video, gaming and brain information. Our survey aims to serve as a valuable resource for researchers and practitioners to navigate the rapidly expanding landscape of generative AI, facilitating a better understanding of the current state-of-the-art and fostering further innovation in the field.

Please click each post's URL shown below to check out its full contents.

3.more LLM basics - a survey

BasicLLM

Summary of Post :

In this session, our readings cover:

Required Readings:

Large Language Models: A Survey

  • Shervin Minaee, Tomas Mikolov, Narjes Nikzad, Meysam Chenaghlu, Richard Socher, Xavier Amatriain, Jianfeng Gao
  • [Submitted on 9 Feb 2024 (v1), last revised 20 Feb 2024 (this version, v2)]
  • Large Language Models (LLMs) have drawn a lot of attention due to their strong performance on a wide range of natural language tasks, since the release of ChatGPT in November 2022. LLMs’ ability of general-purpose language understanding and generation is acquired by training billions of model’s parameters on massive amounts of text data, as predicted by scaling laws \cite{kaplan2020scaling,hoffmann2022training}. The research area of LLMs, while very recent, is evolving rapidly in many different ways. In this paper, we review some of the most prominent LLMs, including three popular LLM families (GPT, LLaMA, PaLM), and discuss their characteristics, contributions and limitations. We also give an overview of techniques developed to build, and augment LLMs. We then survey popular datasets prepared for LLM training, fine-tuning, and evaluation, review widely used LLM evaluation metrics, and compare the performance of several popular LLMs on a set of representative benchmarks. Finally, we conclude the paper by discussing open challenges and future research directions.

Extra Readings:


Please click each post's URL shown below to check out its full contents.

4.Survey - BioScience LLMs

Applications

Summary of Post :

In this session, our readings cover:

Required Readings:

Scientific Large Language Models: A Survey on Biological & Chemical Domains

  • https://arxiv.org/abs/2401.14656
  • Qiang Zhang, Keyang Ding, Tianwen Lyv, Xinda Wang, Qingyu Yin, Yiwen Zhang, Jing Yu, Yuhao Wang, Xiaotong Li, Zhuoyi Xiang, Kehua Feng, Xiang Zhuang, Zeyuan Wang, Ming Qin, Mengyao Zhang, Jinlu Zhang, Jiyu Cui, Tao Huang, Pengju Yan, Renjun Xu, Hongyang Chen, Xiaolin Li, Xiaohui Fan, Huabin Xing, Huajun Chen
  • Large Language Models (LLMs) have emerged as a transformative power in enhancing natural language comprehension, representing a significant stride toward artificial general intelligence. The application of LLMs extends beyond conventional linguistic boundaries, encompassing specialized linguistic systems developed within various scientific disciplines. This growing interest has led to the advent of scientific LLMs, a novel subclass specifically engineered for facilitating scientific discovery. As a burgeoning area in the community of AI for Science, scientific LLMs warrant comprehensive exploration. However, a systematic and up-to-date survey introducing them is currently lacking. In this paper, we endeavor to methodically delineate the concept of “scientific language”, whilst providing a thorough review of the latest advancements in scientific LLMs. Given the expansive realm of scientific disciplines, our analysis adopts a focused lens, concentrating on the biological and chemical domains. This includes an in-depth examination of LLMs for textual knowledge, small molecules, macromolecular proteins, genomic sequences, and their combinations, analyzing them in terms of model architectures, capabilities, datasets, and evaluation. Finally, we critically examine the prevailing challenges and point out promising research directions along with the advances of LLMs. By offering a comprehensive overview of technical developments in this field, this survey aspires to be an invaluable resource for researchers navigating the intricate landscape of scientific LLMs.

Computational Protein Science in the Era of Large Language Models (LLMs)

  • https://arxiv.org/abs/2501.10282
  • Wenqi Fan, Yi Zhou, Shijie Wang, Yuyao Yan, Hui Liu, Qian Zhao, Le Song, Qing Li
  • Considering the significance of proteins, computational protein science has always been a critical scientific field, dedicated to revealing knowledge and developing applications within the protein sequence-structure-function paradigm. In the last few decades, Artificial Intelligence (AI) has made significant impacts in computational protein science, leading to notable successes in specific protein modeling tasks. However, those previous AI models still meet limitations, such as the difficulty in comprehending the semantics of protein sequences, and the inability to generalize across a wide range of protein modeling tasks. Recently, LLMs have emerged as a milestone in AI due to their unprecedented language processing & generalization capability. They can promote comprehensive progress in fields rather than solving individual tasks. As a result, researchers have actively introduced LLM techniques in computational protein science, developing protein Language Models (pLMs) that skillfully grasp the foundational knowledge of proteins and can be effectively generalized to solve a diversity of sequence-structure-function reasoning problems. While witnessing prosperous developments, it’s necessary to present a systematic overview of computational protein science empowered by LLM techniques. First, we summarize existing pLMs into categories based on their mastered protein knowledge, i.e., underlying sequence patterns, explicit structural and functional information, and external scientific languages. Second, we introduce the utilization and adaptation of pLMs, highlighting their remarkable achievements in promoting protein structure prediction, protein function prediction, and protein design studies. Then, we describe the practical application of pLMs in antibody design, enzyme design, and drug discovery. Finally, we specifically discuss the promising future directions in this fast-growing field.

Extra Readings:


Please click each post's URL shown below to check out its full contents.

5.Survey - FMs in healthcare

Applications

Summary of Post :

In this session, our readings cover:

Required Readings:

A Comprehensive Survey of Foundation Models in Medicine

  • Khan, Wasif, Seowung Leem, Kyle B. See, Joshua K. Wong, Shaoting Zhang, and Ruogu Fang. “A Comprehensive Survey of Foundation Models in Medicine.” arXiv, January 16, 2025. https://doi.org/10.48550/arXiv.2406.10729.

  • URL
  • Wasif Khan, Seowung Leem, Kyle B. See, Joshua K. Wong, Shaoting Zhang, Ruogu Fang
  • Foundation models (FMs) are large-scale deep-learning models trained on extensive datasets using self-supervised techniques. These models serve as a base for various downstream tasks, including healthcare. FMs have been adopted with great success across various domains within healthcare, including natural language processing (NLP), computer vision, graph learning, biology, and omics. Existing healthcare-based surveys have not yet included all of these domains. Therefore, this survey provides a comprehensive overview of FMs in healthcare. We focus on the history, learning strategies, flagship models, applications, and challenges of FMs. We explore how FMs such as the BERT and GPT families are reshaping various healthcare domains, including clinical large language models, medical image analysis, and omics data. Furthermore, we provide a detailed taxonomy of healthcare applications facilitated by FMs, such as clinical NLP, medical computer vision, graph learning, and other biology-related tasks. Despite the promising opportunities FMs provide, they also have several associated challenges, which are explained in detail. We also outline potential future directions to provide researchers and practitioners with insights into the potential and limitations of FMs in healthcare to advance their deployment and mitigate associated risks.

Foundation Model for Advancing Healthcare: Challenges, Opportunities and Future Directions

  • He, Yuting, Fuxiang Huang, Xinrui Jiang, Yuxiang Nie, Minghao Wang, Jiguang Wang, and Hao Chen. “Foundation Model for Advancing Healthcare: Challenges, Opportunities and Future Directions.” IEEE Reviews in Biomedical Engineering PP (November 12, 2024). https://doi.org/10.1109/RBME.2024.3496744.

  • https://github.com/YutingHe-list/Awesome-Foundation-Models-for-Advancing-Healthcare

  • Abstract: Foundation model, trained on a diverse range of data and adaptable to a myriad of tasks, is advancing healthcare. It fosters the development of healthcare artificial intelligence (AI) models tailored to the intricacies of the medical field, bridging the gap between limited AI models and the varied nature of healthcare practices. The advancement of a healthcare foundation model (HFM) brings forth tremendous potential to augment intelligent healthcare services across a broad spectrum of scenarios. However, despite the imminent widespread deployment of HFMs, there is currently a lack of clear understanding regarding their operation in the healthcare field, their existing challenges, and their future trajectory. To answer these critical inquiries, we present a comprehensive and in-depth examination that delves into the landscape of HFMs. It begins with a comprehensive overview of HFMs, encompassing their methods, data, and applications, to provide a quick understanding of the current progress. Subsequently, it delves into a thorough exploration of the challenges associated with data, algorithms, and computing infrastructures in constructing and widely applying foundation models in healthcare. Furthermore, this survey identifies promising directions for future development in this field. We believe that this survey will enhance the community’s understanding of the current progress of HFMs and serve as a valuable source of guidance for future advancements in this domain. For the latest HFM papers and related resources, please refer to our website.

A Multi-Center Study on the Adaptability of a Shared Foundation Model for Electronic Health Records.

  • Guo, Lin Lawrence, Jason Fries, Ethan Steinberg, Scott Lanyon Fleming, Keith Morse, Catherine Aftandilian, Jose Posada, Nigam Shah, and Lillian Sung. “” Npj Digital Medicine 7, no. 1 (June 27, 2024): 1–9. https://doi.org/10.1038/s41746-024-01166-w.

  • Foundation models are transforming artificial intelligence (AI) in healthcare by providing modular components adaptable for various downstream tasks, making AI development more scalable and cost-effective. Foundation models for structured electronic health records (EHR), trained on coded medical records from millions of patients, demonstrated benefits including increased performance with fewer training labels, and improved robustness to distribution shifts. However, questions remain on the feasibility of sharing these models across hospitals and their performance in local tasks. This multi-center study examined the adaptability of a publicly accessible structured EHR foundation model (FMSM), trained on 2.57 M patient records from Stanford Medicine. Experiments used EHR data from The Hospital for Sick Children (SickKids) and Medical Information Mart for Intensive Care (MIMIC-IV). We assessed both adaptability via continued pretraining on local data, and task adaptability compared to baselines of locally training models from scratch, including a local foundation model. Evaluations on 8 clinical prediction tasks showed that adapting the off-the-shelf FMSM matched the performance of gradient boosting machines (GBM) locally trained on all data while providing a 13% improvement in settings with few task-specific training labels. Continued pretraining on local data showed FMSM required fewer than 1% of training examples to match the fully trained GBM’s performance, and was 60 to 90% more sample-efficient than training local foundation models from scratch. Our findings demonstrate that adapting EHR foundation models across hospitals provides improved prediction performance at less cost, underscoring the utility of base foundation models as modular components to streamline the development of healthcare AI.


Please click each post's URL shown below to check out its full contents.

6.Survey - FMs in Robotics

Applications

Summary of Post :

In this session, our readings cover:

Required Readings:

A Survey on Integration of Large Language Models with Intelligent Robots

  • [Submitted on 14 Apr 2024 (v1), last revised 15 Aug 2024 (this version, v5)]
  • Yeseung Kim, Dohyun Kim, Jieun Choi, Jisang Park, Nayoung Oh, Daehyung Park
  • In recent years, the integration of large language models (LLMs) has revolutionized the field of robotics, enabling robots to communicate, understand, and reason with human-like proficiency. This paper explores the multifaceted impact of LLMs on robotics, addressing key challenges and opportunities for leveraging these models across various domains. By categorizing and analyzing LLM applications within core robotics elements – communication, perception, planning, and control – we aim to provide actionable insights for researchers seeking to integrate LLMs into their robotic systems. Our investigation focuses on LLMs developed post-GPT-3.5, primarily in text-based modalities while also considering multimodal approaches for perception and control. We offer comprehensive guidelines and examples for prompt engineering, facilitating beginners’ access to LLM-based robotics solutions. Through tutorial-level examples and structured prompt construction, we illustrate how LLM-guided enhancements can be seamlessly integrated into robotics applications. This survey serves as a roadmap for researchers navigating the evolving landscape of LLM-driven robotics, offering a comprehensive overview and practical guidance for harnessing the power of language models in robotics development.

Large Language Models for Robotics: Opportunities, Challenges, and Perspectives

  • Jiaqi Wang, Zihao Wu, Yiwei Li, Hanqi Jiang, Peng Shu, Enze Shi, Huawen Hu, Chong Ma, Yiheng Liu, Xuhui Wang, Yincheng Yao, Xuan Liu, Huaqin Zhao, Zhengliang Liu, Haixing Dai, Lin Zhao, Bao Ge, Xiang Li, Tianming Liu, Shu Zhang
  • Large language models (LLMs) have undergone significant expansion and have been increasingly integrated across various domains. Notably, in the realm of robot task planning, LLMs harness their advanced reasoning and language comprehension capabilities to formulate precise and efficient action plans based on natural language instructions. However, for embodied tasks, where robots interact with complex environments, text-only LLMs often face challenges due to a lack of compatibility with robotic visual perception. This study provides a comprehensive overview of the emerging integration of LLMs and multimodal LLMs into various robotic tasks. Additionally, we propose a framework that utilizes multimodal GPT-4V to enhance embodied task planning through the combination of natural language instructions and robot visual perceptions. Our results, based on diverse datasets, indicate that GPT-4V effectively enhances robot performance in embodied tasks. This extensive survey and evaluation of LLMs and multimodal LLMs across a variety of robotic tasks enriches the understanding of LLM-centric embodied intelligence and provides forward-looking insights toward bridging the gap in Human-Robot-Environment interaction.

A Survey of Robot Intelligence with Large Language Models

  • https://doi.org/10.3390/app14198868
  • Submission received: 6 September 2024 / Revised: 24 September 2024 / Accepted: 25 September 2024 / Published: 2 October 2024
  • (This article belongs to the Special Issue Advancements in Intelligent Systems: The Confluence of AI, Machine Learning, and Robotics)
  • Since the emergence of ChatGPT, research on large language models (LLMs) has actively progressed across various fields. LLMs, pre-trained on vast text datasets, have exhibited exceptional abilities in understanding natural language and planning tasks. These abilities of LLMs are promising in robotics. In general, traditional supervised learning-based robot intelligence systems have a significant lack of adaptability to dynamically changing environments. However, LLMs help a robot intelligence system to improve its generalization ability in dynamic and complex real-world environments. Indeed, findings from ongoing robotics studies indicate that LLMs can significantly improve robots’ behavior planning and execution capabilities. Additionally, vision-language models (VLMs), trained on extensive visual and linguistic data for the vision question answering (VQA) problem, excel at integrating computer vision with natural language processing. VLMs can comprehend visual contexts and execute actions through natural language. They also provide descriptions of scenes in natural language. Several studies have explored the enhancement of robot intelligence using multimodal data, including object recognition and description by VLMs, along with the execution of language-driven commands integrated with visual information. This review paper thoroughly investigates how foundation models such as LLMs and VLMs have been employed to boost robot intelligence. For clarity, the research areas are categorized into five topics: reward design in reinforcement learning, low-level control, high-level planning, manipulation, and scene understanding. This review also summarizes studies that show how foundation models, such as the Eureka model for automating reward function design in reinforcement learning, RT-2 for integrating visual data, language, and robot actions in vision-language-action models, and AutoRT for generating feasible tasks and executing robot behavior policies via LLMs, have improved robot intelligence. Keywords: embodied intelligence; foundation model; large language model (LLM); vision-language model (VLM); vision-language-action (VLA) model; robotics

More Readings:


Please click each post's URL shown below to check out its full contents.

7.advanced LLM - for code reasoning

Reasoning

Summary of Post :

In this session, our readings cover:

Required Readings:

Language Models for Code Optimization: Survey, Challenges and Future Directions

  • https://arxiv.org/abs/2501.01277
  • [Submitted on 2 Jan 2025 (v1), last revised 3 Jan 2025 (this version, v2)]
  • Jingzhi Gong, Vardan Voskanyan, Paul Brookes, Fan Wu, Wei Jie, Jie Xu, Rafail Giavrimis, Mike Basios, Leslie Kanthan, Zheng Wang
  • Language models (LMs) built upon deep neural networks (DNNs) have recently demonstrated breakthrough effectiveness in software engineering tasks such as code generation, completion, and repair. This has paved the way for the emergence of LM-based code optimization techniques, which are crucial for enhancing the performance of existing programs, such as accelerating program execution time. However, a comprehensive survey dedicated to this specific application has been lacking. To fill this gap, we present a systematic literature review of over 50 primary studies, identifying emerging trends and addressing 11 specialized questions. Our findings reveal five critical open challenges, such as balancing model complexity with practical usability, cross-language/performance generalizability, and building trust in AI-driven solutions. Furthermore, we provide eight future research directions to facilitate more efficient, robust, and reliable LM-based code optimization. Thereby, this study aims to provide actionable insights and foundational references for both researchers and practitioners in this rapidly evolving field.

DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence

  • https://arxiv.org/abs/2406.11931
  • DeepSeek-AI, Qihao Zhu, Daya Guo, Zhihong Shao, Dejian Yang, Peiyi Wang, Runxin Xu, Y. Wu, + Yukun Li, Huazuo Gao, Shirong Ma, Wangding Zeng, Xiao Bi, Zihui Gu, Hanwei Xu, Damai Dai, Kai Dong, Liyue Zhang, Yishi Piao, Zhibin Gou, Zhenda Xie, Zhewen Hao, Bingxuan Wang, Junxiao Song, Deli Chen, Xin Xie, Kang Guan, Yuxiang You, Aixin Liu, Qiushi Du, Wenjun Gao, Xuan Lu, Qinyu Chen, Yaohui Wang, Chengqi Deng, Jiashi Li, Chenggang Zhao, Chong Ruan, Fuli Luo, Wenfeng Liang
  • We present DeepSeek-Coder-V2, an open-source Mixture-of-Experts (MoE) code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks. Specifically, DeepSeek-Coder-V2 is further pre-trained from an intermediate checkpoint of DeepSeek-V2 with additional 6 trillion tokens. Through this continued pre-training, DeepSeek-Coder-V2 substantially enhances the coding and mathematical reasoning capabilities of DeepSeek-V2, while maintaining comparable performance in general language tasks. Compared to DeepSeek-Coder-33B, DeepSeek-Coder-V2 demonstrates significant advancements in various aspects of code-related tasks, as well as reasoning and general capabilities. Additionally, DeepSeek-Coder-V2 expands its support for programming languages from 86 to 338, while extending the context length from 16K to 128K. In standard benchmark evaluations, DeepSeek-Coder-V2 achieves superior performance compared to closed-source models such as GPT4-Turbo, Claude 3 Opus, and Gemini 1.5 Pro in coding and math benchmarks.

Iterative Refinement of Project-Level Code Context for Precise Code Generation with Compiler Feedback

  • [Submitted on 25 Mar 2024 (v1), last revised 11 Jun 2024 (this version, v3)]
  • Zhangqian Bi, Yao Wan, Zheng Wang, Hongyu Zhang, Batu Guan, Fangxin Lu, Zili Zhang, Yulei Sui, Hai Jin, Xuanhua Shi
  • Large Language Models (LLMs) have shown remarkable progress in automated code generation. Yet, LLM-generated code may contain errors in API usage, class, data structure, or missing project-specific information. As much of this project-specific context cannot fit into the prompts of LLMs, we must find ways to allow the model to explore the project-level code context. We present CoCoGen, a new code generation approach that uses compiler feedback to improve the LLM-generated code. CoCoGen first leverages static analysis to identify mismatches between the generated code and the project’s context. It then iteratively aligns and fixes the identified errors using information extracted from the code repository. We integrate CoCoGen with two representative LLMs, i.e., GPT-3.5-Turbo and Code Llama (13B), and apply it to Python code generation. Experimental results show that CoCoGen significantly improves the vanilla LLMs by over 80% in generating code dependent on the project context and consistently outperforms the existing retrieval-based code generation baselines.

More Readings:


Please click each post's URL shown below to check out its full contents.

8.advanced LLM - Math reasoning

Reasoning

Summary of Post :

In this session, our readings cover:

Required Readings:

Solving olympiad geometry without human demonstrations

  • Trieu H. Trinh, Yuhuai Wu, Quoc V. Le, He He & Thang Luong
  • Nature volume 625, pages476–482 (2024)Cite this article
  • Published: 17 January 2024
  • https://www.nature.com/articles/s41586-023-06747-5
  • Proving mathematical theorems at the olympiad level represents a notable milestone in human-level automated reasoning1,2,3,4, owing to their reputed difficulty among the world’s best talents in pre-university mathematics. Current machine-learning approaches, however, are not applicable to most mathematical domains owing to the high cost of translating human proofs into machine-verifiable format. The problem is even worse for geometry because of its unique translation challenges1,5, resulting in severe scarcity of training data. We propose AlphaGeometry, a theorem prover for Euclidean plane geometry that sidesteps the need for human demonstrations by synthesizing millions of theorems and proofs across different levels of complexity. AlphaGeometry is a neuro-symbolic system that uses a neural language model, trained from scratch on our large-scale synthetic data, to guide a symbolic deduction engine through infinite branching points in challenging problems. On a test set of 30 latest olympiad-level problems, AlphaGeometry solves 25, outperforming the previous best method that only solves ten problems and approaching the performance of an average International Mathematical Olympiad (IMO) gold medallist. Notably, AlphaGeometry produces human-readable proofs, solves all geometry problems in the IMO 2000 and 2015 under human expert evaluation and discovers a generalized version of a translated IMO theorem in 2004.

Mathematical discoveries from program search with large language models

  • Published: 14 December 2023
  • Bernardino Romera-Paredes, Mohammadamin Barekatain, Alexander Novikov, Matej Balog, M. Pawan Kumar, Emilien Dupont, Francisco J. R. Ruiz, Jordan S. Ellenberg, Pengming Wang, Omar Fawzi, Pushmeet Kohli & Alhussein Fawzi
  • Nature https://www.nature.com/articles/s41586-023-06924-6#auth-Bernardino-Romera_Paredes-Aff1
  • Large language models (LLMs) have demonstrated tremendous capabilities in solving complex tasks, from quantitative reasoning to understanding natural language. However, LLMs sometimes suffer from confabulations (or hallucinations), which can result in them making plausible but incorrect statements1,2. This hinders the use of current large models in scientific discovery. Here we introduce FunSearch (short for searching in the function space), an evolutionary procedure based on pairing a pretrained LLM with a systematic evaluator. We demonstrate the effectiveness of this approach to surpass the best-known results in important problems, pushing the boundary of existing LLM-based approaches3. Applying FunSearch to a central problem in extremal combinatorics—the cap set problem—we discover new constructions of large cap sets going beyond the best-known ones, both in finite dimensional and asymptotic cases. This shows that it is possible to make discoveries for established open problems using LLMs. We showcase the generality of FunSearch by applying it to an algorithmic problem, online bin packing, finding new heuristics that improve on widely used baselines. In contrast to most computer search approaches, FunSearch searches for programs that describe how to solve a problem, rather than what the solution is. Beyond being an effective and scalable strategy, discovered programs tend to be more interpretable than raw solutions, enabling feedback loops between domain experts and FunSearch, and the deployment of such programs in real-world applications.

DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

  • Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, Y.K. Li, Y. Wu, Daya Guo
  • Mathematical reasoning poses a significant challenge for language models due to its complex and structured nature. In this paper, we introduce DeepSeekMath 7B, which continues pre-training DeepSeek-Coder-Base-v1.5 7B with 120B math-related tokens sourced from Common Crawl, together with natural language and code data. DeepSeekMath 7B has achieved an impressive score of 51.7% on the competition-level MATH benchmark without relying on external toolkits and voting techniques, approaching the performance level of Gemini-Ultra and GPT-4. Self-consistency over 64 samples from DeepSeekMath 7B achieves 60.9% on MATH. The mathematical reasoning capability of DeepSeekMath is attributed to two key factors: First, we harness the significant potential of publicly available web data through a meticulously engineered data selection pipeline. Second, we introduce Group Relative Policy Optimization (GRPO), a variant of Proximal Policy Optimization (PPO), that enhances mathematical reasoning abilities while concurrently optimizing the memory usage of PPO.
  • Elements:
    • Both Deepseek and Qwen use GRPO in post-training! Group Relative Policy Optimization or GRPO was introduced in the DeepSeekMath Paper last year to improve mathematical reasoning capabilities with less memory consumption, but is now used in an online way also to improve Truthfulness, Helpfulness, Conciseness…
    • Generate multiple outputs for each input question using the current Policy
    • Score these outputs using a reward model
    • Average the rewards and use it as a baseline to compute the advantages
    • Update the Policy to maximize the GRPO objective, which includes the advantages and a KL term
  • Insights:
    • Doesn’t need value function model, reducing memory and complexity
    • Adds KL term directly to the loss rather than in the reward
    • Works with rule-based Reward Models and Generative/Score based RM
    • Looks similar to RLOO method
    • DS 3 improved coding, math, writing, role-playing, and question answering

DeepSeek-V3 Technical Report

  • DeepSeek-AI, (100 additional authors not shown)
  • We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. To achieve efficient inference and cost-effective training, DeepSeek-V3 adopts Multi-head Latent Attention (MLA) and DeepSeekMoE architectures, which were thoroughly validated in DeepSeek-V2. Furthermore, DeepSeek-V3 pioneers an auxiliary-loss-free strategy for load balancing and sets a multi-token prediction training objective for stronger performance. We pre-train DeepSeek-V3 on 14.8 trillion diverse and high-quality tokens, followed by Supervised Fine-Tuning and Reinforcement Learning stages to fully harness its capabilities. Comprehensive evaluations reveal that DeepSeek-V3 outperforms other open-source models and achieves performance comparable to leading closed-source models. Despite its excellent performance, DeepSeek-V3 requires only 2.788M H800 GPU hours for its full training. In addition, its training process is remarkably stable. Throughout the entire training process, we did not experience any irrecoverable loss spikes or perform any rollbacks. The model checkpoints are available at this https URL.

More Readings:

Large Language Models for Mathematical Reasoning: Progresses and Challenges

  • Janice Ahn, Rishu Verma, Renze Lou, Di Liu, Rui Zhang, Wenpeng Yin
  • [Submitted on 31 Jan 2024 (v1), last revised 16 Sep 2024 (this version, v4)]
  • Mathematical reasoning serves as a cornerstone for assessing the fundamental cognitive capabilities of human intelligence. In recent times, there has been a notable surge in the development of Large Language Models (LLMs) geared towards the automated resolution of mathematical problems. However, the landscape of mathematical problem types is vast and varied, with LLM-oriented techniques undergoing evaluation across diverse datasets and settings. This diversity makes it challenging to discern the true advancements and obstacles within this burgeoning field. This survey endeavors to address four pivotal dimensions: i) a comprehensive exploration of the various mathematical problems and their corresponding datasets that have been investigated; ii) an examination of the spectrum of LLM-oriented techniques that have been proposed for mathematical problem-solving; iii) an overview of factors and concerns affecting LLMs in solving math; and iv) an elucidation of the persisting challenges within this domain. To the best of our knowledge, this survey stands as one of the first extensive examinations of the landscape of LLMs in the realm of mathematics, providing a holistic perspective on the current state, accomplishments, and future challenges in this rapidly evolving field.

A Survey of Deep Learning for Mathematical Reasoning

  • Pan Lu, Liang Qiu, Wenhao Yu, Sean Welleck, Kai-Wei Chang
  • [Submitted on 20 Dec 2022 (v1), last revised 22 Jun 2023 (this version, v2)]
  • Mathematical reasoning is a fundamental aspect of human intelligence and is applicable in various fields, including science, engineering, finance, and everyday life. The development of artificial intelligence (AI) systems capable of solving math problems and proving theorems has garnered significant interest in the fields of machine learning and natural language processing. For example, mathematics serves as a testbed for aspects of reasoning that are challenging for powerful deep learning models, driving new algorithmic and modeling advances. On the other hand, recent advances in large-scale neural language models have opened up new benchmarks and opportunities to use deep learning for mathematical reasoning. In this survey paper, we review the key tasks, datasets, and methods at the intersection of mathematical reasoning and deep learning over the past decade. We also evaluate existing benchmarks and methods, and discuss future research directions in this domain.

AI Capabilities Can Be Significantly Improved Without Expensive Retraining

  • https://epoch.ai/blog/ai-capabilities-can-be-significantly-improved-without-expensive-retraining

Please click each post's URL shown below to check out its full contents.

9.Platform - Prompting Engineering tools / Prompt Compression

Prompting

Summary of Post :

In this session, our readings cover:

Required Readings:

The Prompt Report: A Systematic Survey of Prompting Techniques

  • URL
  • [Submitted on 6 Jun 2024 (v1), last revised 30 Dec 2024 (this version, v5)]
  • Sander Schulhoff, Michael Ilie, Nishant Balepur, Konstantine Kahadze, Amanda Liu, Chenglei Si, Yinheng Li, Aayush Gupta, HyoJung Han, Sevien Schulhoff, Pranav Sandeep Dulepet, Saurav Vidyadhara, Dayeon Ki, Sweta Agrawal, Chau Pham, Gerson Kroiz, Feileen Li, Hudson Tao, Ashay Srivastava, Hevander Da Costa, Saloni Gupta, Megan L. Rogers, Inna Goncearenco, Giuseppe Sarli, Igor Galynker, Denis Peskoff, Marine Carpuat, Jules White, Shyamal Anadkat, Alexander Hoyle, Philip Resnik
  • Generative Artificial Intelligence (GenAI) systems are increasingly being deployed across diverse industries and research domains. Developers and end-users interact with these systems through the use of prompting and prompt engineering. Although prompt engineering is a widely adopted and extensively researched area, it suffers from conflicting terminology and a fragmented ontological understanding of what constitutes an effective prompt due to its relatively recent emergence. We establish a structured understanding of prompt engineering by assembling a taxonomy of prompting techniques and analyzing their applications. We present a detailed vocabulary of 33 vocabulary terms, a taxonomy of 58 LLM prompting techniques, and 40 techniques for other modalities. Additionally, we provide best practices and guidelines for prompt engineering, including advice for prompting state-of-the-art (SOTA) LLMs such as ChatGPT. We further present a meta-analysis of the entire literature on natural language prefix-prompting. As a culmination of these efforts, this paper presents the most comprehensive survey on prompt engineering to date.

Prompt Compression for Large Language Models: A Survey

  • [Submitted on 16 Oct 2024 (v1), last revised 17 Oct 2024 (this version, v2)]
  • URL
  • Zongqian Li, Yinhong Liu, Yixuan Su, Nigel Collier
  • Leveraging large language models (LLMs) for complex natural language tasks typically requires long-form prompts to convey detailed requirements and information, which results in increased memory usage and inference costs. To mitigate these challenges, multiple efficient methods have been proposed, with prompt compression gaining significant research interest. This survey provides an overview of prompt compression techniques, categorized into hard prompt methods and soft prompt methods. First, the technical approaches of these methods are compared, followed by an exploration of various ways to understand their mechanisms, including the perspectives of attention optimization, Parameter-Efficient Fine-Tuning (PEFT), modality integration, and new synthetic language. We also examine the downstream adaptations of various prompt compression techniques. Finally, the limitations of current prompt compression methods are analyzed, and several future directions are outlined, such as optimizing the compression encoder, combining hard and soft prompts methods, and leveraging insights from multimodality.

More Readings:

Harnessing the Power of Multiple Minds: Lessons Learned from LLM Routing

  • KV Aditya Srivatsa, Kaushal Kumar Maurya, Ekaterina Kochmar
  • With the rapid development of LLMs, it is natural to ask how to harness their capabilities efficiently. In this paper, we explore whether it is feasible to direct each input query to a single most suitable LLM. To this end, we propose LLM routing for challenging reasoning tasks. Our extensive experiments suggest that such routing shows promise but is not feasible in all scenarios, so more robust approaches should be investigated to fill this gap.

Please click each post's URL shown below to check out its full contents.

10.Platform - Context construction via RAG and Agent

RAG Agent

Summary of Post :

In this session, our readings cover:

Required Readings:

ReAct: Synergizing Reasoning and Acting in Language Models

  • https://arxiv.org/abs/2210.03629
  • Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, Yuan Cao
  • [Submitted on 6 Oct 2022 (v1), last revised 10 Mar 2023 (this version, v3)]
  • While large language models (LLMs) have demonstrated impressive capabilities across tasks in language understanding and interactive decision making, their abilities for reasoning (e.g. chain-of-thought prompting) and acting (e.g. action plan generation) have primarily been studied as separate topics. In this paper, we explore the use of LLMs to generate both reasoning traces and task-specific actions in an interleaved manner, allowing for greater synergy between the two: reasoning traces help the model induce, track, and update action plans as well as handle exceptions, while actions allow it to interface with external sources, such as knowledge bases or environments, to gather additional information. We apply our approach, named ReAct, to a diverse set of language and decision making tasks and demonstrate its effectiveness over state-of-the-art baselines, as well as improved human interpretability and trustworthiness over methods without reasoning or acting components. Concretely, on question answering (HotpotQA) and fact verification (Fever), ReAct overcomes issues of hallucination and error propagation prevalent in chain-of-thought reasoning by interacting with a simple Wikipedia API, and generates human-like task-solving trajectories that are more interpretable than baselines without reasoning traces. On two interactive decision making benchmarks (ALFWorld and WebShop), ReAct outperforms imitation and reinforcement learning methods by an absolute success rate of 34% and 10% respectively, while being prompted with only one or two in-context examples. Project site with code: this https URL

Agent white paper

  • https://www.kaggle.com/whitepaper-agents
  • Google recently published a whitepaper on AI Agents that everyone should read. It covers everything you need to know about this new wave.
    • Introduction to AI Agents
    • The role of tools in Agents
    • Enhancing model performance with targeted learning
    • Quick start to Agents with LangChain
    • Production applications with Vertex AI Agents

Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG

  • [Submitted on 15 Jan 2025]
  • Aditi Singh, Abul Ehtesham, Saket Kumar, Tala Talaei Khoei
  • Large Language Models (LLMs) have revolutionized artificial intelligence (AI) by enabling human like text generation and natural language understanding. However, their reliance on static training data limits their ability to respond to dynamic, real time queries, resulting in outdated or inaccurate outputs. Retrieval Augmented Generation (RAG) has emerged as a solution, enhancing LLMs by integrating real time data retrieval to provide contextually relevant and up-to-date responses. Despite its promise, traditional RAG systems are constrained by static workflows and lack the adaptability required for multistep reasoning and complex task management. Agentic Retrieval-Augmented Generation (Agentic RAG) transcends these limitations by embedding autonomous AI agents into the RAG pipeline. These agents leverage agentic design patterns reflection, planning, tool use, and multiagent collaboration to dynamically manage retrieval strategies, iteratively refine contextual understanding, and adapt workflows to meet complex task requirements. This integration enables Agentic RAG systems to deliver unparalleled flexibility, scalability, and context awareness across diverse applications. This survey provides a comprehensive exploration of Agentic RAG, beginning with its foundational principles and the evolution of RAG paradigms. It presents a detailed taxonomy of Agentic RAG architectures, highlights key applications in industries such as healthcare, finance, and education, and examines practical implementation strategies. Additionally, it addresses challenges in scaling these systems, ensuring ethical decision making, and optimizing performance for real-world applications, while providing detailed insights into frameworks and tools for implementing Agentic RAG

More Readings:


Please click each post's URL shown below to check out its full contents.

11.Platform - Agent Tooling

Agent

Summary of Post :

In this session, our readings cover:

Required Readings:

eBook: Mastering AI Agents

  • Learn how to create powerful, reliable AI agents with Galileo’s in-depth eBook
  • URL
  • The book is divided into five chapters:
  • Chapter 1 introduces AI agents, their optimal applications, and scenarios where they might be excessive. It covers various agent types and includes three real-world use cases to illustrate their potential.
  • Chapter 2 details three frameworks—LangGraph, Autogen, and CrewAI—with evaluation criteria to help choose the best fit. It ends with case studies of companies using these frameworks for specific AI tasks.
  • Chapter 3 explores the evaluation of an AI agent through a step-by-step example of a finance research agent.
  • Chapter 4 explores how to measure agent performance across systems, task completion, quality control, and tool interaction, supported by five detailed use cases.
  • Chapter 5 addresses why many AI agents fail and offers practical solutions for successful AI deployment.

More Readings:


Please click each post's URL shown below to check out its full contents.

12.Platform - More agent related

Agent

Summary of Post :

In this session, our readings cover:

Required Readings:

Agent Tools/Libraries:

Introduces a cohesive AutoGen ecosystem that includes the framework, developer tools, and applications. The framework’s layered architecture clearly defines each layer’s functionality. It supports both first-party and third-party applications and extensions. Microsoft Research announces AutoGen v0.4, a major update to their multi-agent AI framework. The new version introduces a complete redesign with an asynchronous, event-driven architecture that improves code quality, robustness, and scalability. Key features include modular components, built-in debugging tools, cross-language support, and enhanced observability through OpenTelemetry integration.

The update brings a new three-layered framework architecture consisting of core building blocks, AgentChat API, and extensions. It also introduces improved developer tools including AutoGen Bench for performance testing, an upgraded AutoGen Studio with real-time agent updates and visual team building, and Magentic-One, a new generalist multi-agent application for handling web and file-based tasks. The release maintains backward compatibility through the AgentChat API, making the migration from v0.2 straightforward while adding new capabilities like streaming messages and improved task progress management.

  • https://docs.ag2.ai/docs/blog/2025-02-13-DeepResearchAgent/index

one Survey Blogpost on agent2024 …

  • https://open.substack.com/pub/victordibia/p/ai-agents-2024-rewind-a-year-of-building?r=ya7nu&utm_medium=ios

OpenAI Operator

  • https://cdn.openai.com/operator_system_card.pdf
  • “OpenAI introduces Operator, a research preview of a browser-controlling agent available to Pro users in the U.S. Powered by the Computer-Using Agent (CUA) model, Operator can perform web-based tasks like filling forms, ordering groceries, and creating memes by interacting with graphical interfaces through typing, clicking, and scrolling. The agent leverages GPT-4o’s vision capabilities and reinforcement learning to navigate websites without requiring API integrations.”
  • “multiple safety features, including user takeover mode for sensitive information, task limitations, and defenses against malicious websites. OpenAI is partnering with companies like DoorDash, Instacart, and Uber to refine the technology, while also exploring public sector applications. “

Image

More Readings:


Please click each post's URL shown below to check out its full contents.

13.Platform - Model Jailbreaking / Safeguarding

Jailbreaking Safeguarding

Summary of Post :

In this session, our readings cover:

Required Readings:

Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming

  • Mrinank Sharma, Meg Tong, Jesse Mu, Jerry Wei, Jorrit Kruthoff, Scott Goodfriend, Euan Ong, Alwin Peng, Raj Agarwal, Cem Anil, Amanda Askell, Nathan Bailey, Joe Benton, Emma Bluemke, Samuel R. Bowman, Eric Christiansen, Hoagy Cunningham, Andy Dau, Anjali Gopal, Rob Gilson, Logan Graham, Logan Howard, Nimit Kalra, Taesung Lee, Kevin Lin, Peter Lofgren, Francesco Mosconi, Clare O’Hara, Catherine Olsson, Linda Petrini, Samir Rajani, Nikhil Saxena, Alex Silverstein, Tanya Singh, Theodore Sumers, Leonard Tang, Kevin K. Troy, Constantin Weisser, Ruiqi Zhong, Giulio Zhou, Jan Leike, Jared Kaplan, Ethan Perez
  • [Submitted on 31 Jan 2025]
  • Large language models (LLMs) are vulnerable to universal jailbreaks-prompting strategies that systematically bypass model safeguards and enable users to carry out harmful processes that require many model interactions, like manufacturing illegal substances at scale. To defend against these attacks, we introduce Constitutional Classifiers: safeguards trained on synthetic data, generated by prompting LLMs with natural language rules (i.e., a constitution) specifying permitted and restricted content. In over 3,000 estimated hours of red teaming, no red teamer found a universal jailbreak that could extract information from an early classifier-guarded LLM at a similar level of detail to an unguarded model across most target queries. On automated evaluations, enhanced classifiers demonstrated robust defense against held-out domain-specific jailbreaks. These classifiers also maintain deployment viability, with an absolute 0.38% increase in production-traffic refusals and a 23.7% inference overhead. Our work demonstrates that defending against universal jailbreaks while maintaining practical deployment viability is tractable.

A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models

  • Zihao Xu, Yi Liu, Gelei Deng, Yuekang Li, Stjepan Picek
  • [Submitted on 21 Feb 2024 (v1), last revised 17 May 2024 (this version, v2)]
  • Large Language Models (LLMS) have increasingly become central to generating content with potential societal impacts. Notably, these models have demonstrated capabilities for generating content that could be deemed harmful. To mitigate these risks, researchers have adopted safety training techniques to align model outputs with societal values to curb the generation of malicious content. However, the phenomenon of “jailbreaking”, where carefully crafted prompts elicit harmful responses from models, persists as a significant challenge. This research conducts a comprehensive analysis of existing studies on jailbreaking LLMs and their defense techniques. We meticulously investigate nine attack techniques and seven defense techniques applied across three distinct language models: Vicuna, LLama, and GPT-3.5 Turbo. We aim to evaluate the effectiveness of these attack and defense techniques. Our findings reveal that existing white-box attacks underperform compared to universal techniques and that including special tokens in the input significantly affects the likelihood of successful attacks. This research highlights the need to concentrate on the security facets of LLMs. Additionally, we contribute to the field by releasing our datasets and testing framework, aiming to foster further research into LLM security. We believe these contributions will facilitate the exploration of security measures within this domain. Comments: 18 pages, 9 figures, Accepted in ACL 2024

More Readings:

Auditing Prompt Caching in Language Model APIs

  • [Submitted on 11 Feb 2025]
  • https://arxiv.org/abs/2502.07776
  • Chenchen Gu, Xiang Lisa Li, Rohith Kuditipudi, Percy Liang, Tatsunori Hashimoto
  • Prompt caching in large language models (LLMs) results in data-dependent timing variations: cached prompts are processed faster than non-cached prompts. These timing differences introduce the risk of side-channel timing attacks. For example, if the cache is shared across users, an attacker could identify cached prompts from fast API response times to learn information about other users’ prompts. Because prompt caching may cause privacy leakage, transparency around the caching policies of API providers is important. To this end, we develop and conduct statistical audits to detect prompt caching in real-world LLM API providers. We detect global cache sharing across users in seven API providers, including OpenAI, resulting in potential privacy leakage about users’ prompts. Timing variations due to prompt caching can also result in leakage of information about model architecture. Namely, we find evidence that OpenAI’s embedding model is a decoder-only Transformer, which was previously not publicly known.

New GenAI simulation and evaluation tools in Azure AI Studio

  • https://techcommunity.microsoft.com/blog/aiplatformblog/new-genai-simulation-and-evaluation-tools-in-azure-ai-studio/4253020

LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods

  • Haitao Li, Qian Dong, Junjie Chen, Huixue Su, Yujia Zhou, Qingyao Ai, Ziyi Ye, Yiqun Liu
  • [Submitted on 7 Dec 2024 (v1), last revised 10 Dec 2024 (this version, v2)]
  • The rapid advancement of Large Language Models (LLMs) has driven their expanding application across various fields. One of the most promising applications is their role as evaluators based on natural language responses, referred to as ‘‘LLMs-as-judges’’. This framework has attracted growing attention from both academia and industry due to their excellent effectiveness, ability to generalize across tasks, and interpretability in the form of natural language. This paper presents a comprehensive survey of the LLMs-as-judges paradigm from five key perspectives: Functionality, Methodology, Applications, Meta-evaluation, and Limitations. We begin by providing a systematic definition of LLMs-as-Judges and introduce their functionality (Why use LLM judges?). Then we address methodology to construct an evaluation system with LLMs (How to use LLM judges?). Additionally, we investigate the potential domains for their application (Where to use LLM judges?) and discuss methods for evaluating them in various contexts (How to evaluate LLM judges?). Finally, we provide a detailed analysis of the limitations of LLM judges and discuss potential future directions. Through a structured and comprehensive analysis, we aim aims to provide insights on the development and application of LLMs-as-judges in both research and practice. We will continue to maintain the relevant resource list at this https URL.

Beyond Benchmarks: On The False Promise of AI Regulation

  • [Submitted on 26 Jan 2025] Gabriel Stanovsky, Renana Keydar, Gadi Perl, Eliya Habba The rapid advancement of artificial intelligence (AI) systems in critical domains like healthcare, justice, and social services has sparked numerous regulatory initiatives aimed at ensuring their safe deployment. Current regulatory frameworks, exemplified by recent US and EU efforts, primarily focus on procedural guidelines while presuming that scientific benchmarking can effectively validate AI safety, similar to how crash tests verify vehicle safety or clinical trials validate drug efficacy. However, this approach fundamentally misunderstands the unique technical challenges posed by modern AI systems. Through systematic analysis of successful technology regulation case studies, we demonstrate that effective scientific regulation requires a causal theory linking observable test outcomes to future performance - for instance, how a vehicle’s crash resistance at one speed predicts its safety at lower speeds. We show that deep learning models, which learn complex statistical patterns from training data without explicit causal mechanisms, preclude such guarantees. This limitation renders traditional regulatory approaches inadequate for ensuring AI safety. Moving forward, we call for regulators to reckon with this limitation, and propose a preliminary two-tiered regulatory framework that acknowledges these constraints: mandating human oversight for high-risk applications while developing appropriate risk communication strategies for lower-risk uses. Our findings highlight the urgent need to reconsider fundamental assumptions in AI regulation and suggest a concrete path forward for policymakers and researchers.

Please click each post's URL shown below to check out its full contents.

14.Platform - VLM Jailbreaking / Probing

Jailbreaking Multimodal

Summary of Post :

In this session, our readings cover:

Required Readings:

garak: A Framework for Security Probing Large Language Models

  • [Submitted on 16 Jun 2024]
  • Leon Derczynski, Erick Galinkin, Jeffrey Martin, Subho Majumdar, Nanna Inie As Large Language Models (LLMs) are deployed and integrated into thousands of applications, the need for scalable evaluation of how models respond to adversarial attacks grows rapidly. However, LLM security is a moving target: models produce unpredictable output, are constantly updated, and the potential adversary is highly diverse: anyone with access to the internet and a decent command of natural language. Further, what constitutes a security weak in one context may not be an issue in a different context; one-fits-all guardrails remain theoretical. In this paper, we argue that it is time to rethink what constitutes ``LLM security’’, and pursue a holistic approach to LLM security evaluation, where exploration and discovery of issues are central. To this end, this paper introduces garak (Generative AI Red-teaming and Assessment Kit), a framework which can be used to discover and identify vulnerabilities in a target LLM or dialog system. garak probes an LLM in a structured fashion to discover potential vulnerabilities. The outputs of the framework describe a target model’s weaknesses, contribute to an informed discussion of what composes vulnerabilities in unique contexts, and can inform alignment and policy discussions for LLM deployment.

MMJ-Bench: A Comprehensive Study on Jailbreak Attacks and Defenses for Multimodal Large Language Models

  • [Submitted on 16 Aug 2024 (v1), last revised 22 Oct 2024 (this version, v4)]
  • Fenghua Weng, Yue Xu, Chengyan Fu, Wenjie Wang
  • As deep learning advances, Large Language Models (LLMs) and their multimodal counterparts, Multimodal Large Language Models (MLLMs), have shown exceptional performance in many real-world tasks. However, MLLMs face significant security challenges, such as jailbreak attacks, where attackers attempt to bypass the model’s safety alignment to elicit harmful responses. The threat of jailbreak attacks on MLLMs arises from both the inherent vulnerabilities of LLMs and the multiple information channels that MLLMs process. While various attacks and defenses have been proposed, there is a notable gap in unified and comprehensive evaluations, as each method is evaluated on different dataset and metrics, making it impossible to compare the effectiveness of each method. To address this gap, we introduce \textit{MMJ-Bench}, a unified pipeline for evaluating jailbreak attacks and defense techniques for MLLMs. Through extensive experiments, we assess the effectiveness of various attack methods against SoTA MLLMs and evaluate the impact of defense mechanisms on both defense effectiveness and model utility for normal tasks. Our comprehensive evaluation contribute to the field by offering a unified and systematic evaluation framework and the first public-available benchmark for MLLM jailbreak research. We also demonstrate several insightful findings that highlights directions for future studies.

More Readings:

Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs

  • Zhao Xu, Fan Liu, Hao Liu
  • [Submitted on 13 Jun 2024 (v1), last revised 6 Nov 2024 (this version, v3)]
  • Although Large Language Models (LLMs) have demonstrated significant capabilities in executing complex tasks in a zero-shot manner, they are susceptible to jailbreak attacks and can be manipulated to produce harmful outputs. Recently, a growing body of research has categorized jailbreak attacks into token-level and prompt-level attacks. However, previous work primarily overlooks the diverse key factors of jailbreak attacks, with most studies concentrating on LLM vulnerabilities and lacking exploration of defense-enhanced LLMs. To address these issues, we introduced JailTrickBench to evaluate the impact of various attack settings on LLM performance and provide a baseline for jailbreak attacks, encouraging the adoption of a standardized evaluation framework. Specifically, we evaluate the eight key factors of implementing jailbreak attacks on LLMs from both target-level and attack-level perspectives. We further conduct seven representative jailbreak attacks on six defense methods across two widely used datasets, encompassing approximately 354 experiments with about 55,000 GPU hours on A800-80G. Our experimental results highlight the need for standardized benchmarking to evaluate these attacks on defense-enhanced LLMs. Our code is available at this https URL.

Jailbreak Attacks and Defenses Against Large Language Models: A Survey

  • Sibo Yi, Yule Liu, Zhen Sun, Tianshuo Cong, Xinlei He, Jiaxing Song, Ke Xu, Qi Li
  • [Submitted on 5 Jul 2024 (v1), last revised 30 Aug 2024 (this version, v2)]
  • Large Language Models (LLMs) have performed exceptionally in various text-generative tasks, including question answering, translation, code completion, etc. However, the over-assistance of LLMs has raised the challenge of “jailbreaking”, which induces the model to generate malicious responses against the usage policy and society by designing adversarial prompts. With the emergence of jailbreak attack methods exploiting different vulnerabilities in LLMs, the corresponding safety alignment measures are also evolving. In this paper, we propose a comprehensive and detailed taxonomy of jailbreak attack and defense methods. For instance, the attack methods are divided into black-box and white-box attacks based on the transparency of the target model. Meanwhile, we classify defense methods into prompt-level and model-level defenses. Additionally, we further subdivide these attack and defense methods into distinct sub-classes and present a coherent diagram illustrating their relationships. We also conduct an investigation into the current evaluation methods and compare them from different perspectives. Our findings aim to inspire future research and practical implementations in safeguarding LLMs against adversarial attacks. Above all, although jailbreak remains a significant concern within the community, we believe that our work enhances the understanding of this domain and provides a foundation for developing more secure LLMs.

Safeguarding Large Language Models: A Survey

  • [Submitted on 3 Jun 2024]
  • Yi Dong, Ronghui Mu, Yanghao Zhang, Siqi Sun, Tianle Zhang, Changshun Wu, Gaojie Jin, Yi Qi, Jinwei Hu, Jie Meng, Saddek Bensalem, Xiaowei Huang
  • In the burgeoning field of Large Language Models (LLMs), developing a robust safety mechanism, colloquially known as “safeguards” or “guardrails”, has become imperative to ensure the ethical use of LLMs within prescribed boundaries. This article provides a systematic literature review on the current status of this critical mechanism. It discusses its major challenges and how it can be enhanced into a comprehensive mechanism dealing with ethical issues in various contexts. First, the paper elucidates the current landscape of safeguarding mechanisms that major LLM service providers and the open-source community employ. This is followed by the techniques to evaluate, analyze, and enhance some (un)desirable properties that a guardrail might want to enforce, such as hallucinations, fairness, privacy, and so on. Based on them, we review techniques to circumvent these controls (i.e., attacks), to defend the attacks, and to reinforce the guardrails. While the techniques mentioned above represent the current status and the active research trends, we also discuss several challenges that cannot be easily dealt with by the methods and present our vision on how to implement a comprehensive guardrail through the full consideration of multi-disciplinary approach, neural-symbolic method, and systems development lifecycle.

Please click each post's URL shown below to check out its full contents.

15.Platform - Model Customization - instruction tuning / LoRA

Customization

Summary of Post :

In this session, our readings cover:

Required Readings:

Low-Rank Adaptation for Foundation Models: A Comprehensive Review

  • Menglin Yang, Jialin Chen, Yifei Zhang, Jiahong Liu, Jiasheng Zhang, Qiyao Ma, Harshit Verma, Qianru Zhang, Min Zhou, Irwin King, Rex Ying
  • [Submitted on 31 Dec 2024]
  • The rapid advancement of foundation modelslarge-scale neural networks trained on diverse, extensive datasetshas revolutionized artificial intelligence, enabling unprecedented advancements across domains such as natural language processing, computer vision, and scientific discovery. However, the substantial parameter count of these models, often reaching billions or trillions, poses significant challenges in adapting them to specific downstream tasks. Low-Rank Adaptation (LoRA) has emerged as a highly promising approach for mitigating these challenges, offering a parameter-efficient mechanism to fine-tune foundation models with minimal computational overhead. This survey provides the first comprehensive review of LoRA techniques beyond large Language Models to general foundation models, including recent techniques foundations, emerging frontiers and applications of low-rank adaptation across multiple domains. Finally, this survey discusses key challenges and future research directions in theoretical understanding, scalability, and robustness. This survey serves as a valuable resource for researchers and practitioners working with efficient foundation model adaptation.

SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

  • [Submitted on 28 Jan 2025]
  • Tianzhe Chu, Yuexiang Zhai, Jihan Yang, Shengbang Tong, Saining Xie, Dale Schuurmans, Quoc V. Le, Sergey Levine, Yi Ma
  • Supervised fine-tuning (SFT) and reinforcement learning (RL) are widely used post-training techniques for foundation models. However, their roles in enhancing model generalization capabilities remain unclear. This paper studies the difference between SFT and RL on generalization and memorization, focusing on text-based rule variants and visual variants. We introduce GeneralPoints, an arithmetic reasoning card game, and adopt V-IRL, a real-world navigation environment, to assess how models trained with SFT and RL generalize to unseen variants in both textual and visual domains. We show that RL, especially when trained with an outcome-based reward, generalizes across both rule-based textual and visual variants. SFT, in contrast, tends to memorize training data and struggles to generalize out-of-distribution scenarios. Further analysis reveals that RL improves the model’s underlying visual recognition capabilities, contributing to its enhanced generalization in the visual domain. Despite RL’s superior generalization, we show that SFT remains essential for effective RL training; SFT stabilizes the model’s output format, enabling subsequent RL to achieve its performance gains. These findings demonstrates the capability of RL for acquiring generalizable knowledge in complex, multi-modal tasks. Comments: Website at this https URL

DoRA: Weight-Decomposed Low-Rank Adaptation

  • [Submitted on 14 Feb 2024 (v1), last revised 9 Jul 2024 (this version, v6)]
  • Shih-Yang Liu, Chien-Yi Wang, Hongxu Yin, Pavlo Molchanov, Yu-Chiang Frank Wang, Kwang-Ting Cheng, Min-Hung Chen
  • Among the widely used parameter-efficient fine-tuning (PEFT) methods, LoRA and its variants have gained considerable popularity because of avoiding additional inference costs. However, there still often exists an accuracy gap between these methods and full fine-tuning (FT). In this work, we first introduce a novel weight decomposition analysis to investigate the inherent differences between FT and LoRA. Aiming to resemble the learning capacity of FT from the findings, we propose Weight-Decomposed Low-Rank Adaptation (DoRA). DoRA decomposes the pre-trained weight into two components, magnitude and direction, for fine-tuning, specifically employing LoRA for directional updates to efficiently minimize the number of trainable parameters. By employing \ours, we enhance both the learning capacity and training stability of LoRA while avoiding any additional inference overhead. \ours~consistently outperforms LoRA on fine-tuning LLaMA, LLaVA, and VL-BART on various downstream tasks, such as commonsense reasoning, visual instruction tuning, and image/video-text understanding. Code is available at this https URL.

More Readings:


Please click each post's URL shown below to check out its full contents.

16.Platform - Model Serving + PPO

Customization Serving

Summary of Post :

In this session, our readings cover:

Required Readings:

Efficient Memory Management for Large Language Model Serving with PagedAttention

  • Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph E. Gonzalez, Hao Zhang, Ion Stoica
  • [Submitted on 12 Sep 2023]
  • High throughput serving of large language models (LLMs) requires batching sufficiently many requests at a time. However, existing systems struggle because the key-value cache (KV cache) memory for each request is huge and grows and shrinks dynamically. When managed inefficiently, this memory can be significantly wasted by fragmentation and redundant duplication, limiting the batch size. To address this problem, we propose PagedAttention, an attention algorithm inspired by the classical virtual memory and paging techniques in operating systems. On top of it, we build vLLM, an LLM serving system that achieves (1) near-zero waste in KV cache memory and (2) flexible sharing of KV cache within and across requests to further reduce memory usage. Our evaluations show that vLLM improves the throughput of popular LLMs by 2-4× with the same level of latency compared to the state-of-the-art systems, such as FasterTransformer and Orca. The improvement is more pronounced with longer sequences, larger models, and more complex decoding algorithms. vLLM’s source code is publicly available at this https URL

Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems

  • covering: vLLM, continuous batching, chunked prefill, fair scheduling, KV cache management, and disaggregated serving,
  • Xupeng Miao, Gabriele Oliaro, Zhihao Zhang, Xinhao Cheng, Hongyi Jin, Tianqi Chen, Zhihao Jia
  • In the rapidly evolving landscape of artificial intelligence (AI), generative large language models (LLMs) stand at the forefront, revolutionizing how we interact with our data. However, the computational intensity and memory consumption of deploying these models present substantial challenges in terms of serving efficiency, particularly in scenarios demanding low latency and high throughput. This survey addresses the imperative need for efficient LLM serving methodologies from a machine learning system (MLSys) research perspective, standing at the crux of advanced AI innovations and practical system optimizations. We provide in-depth analysis, covering a spectrum of solutions, ranging from cutting-edge algorithmic modifications to groundbreaking changes in system designs. The survey aims to provide a comprehensive understanding of the current state and future directions in efficient LLM serving, offering valuable insights for researchers and practitioners in overcoming the barriers of effective LLM deployment, thereby reshaping the future of AI.
  • https://arxiv.org/pdf/2312.15234

A Survey on Large Language Model Acceleration based on KV Cache Management

  • URL
  • [Submitted on 27 Dec 2024 (v1), last revised 2 Jan 2025 (this version, v2)]
  • Haoyang Li, Yiming Li, Anxin Tian, Tianhao Tang, Zhanchao Xu, Xuejia Chen, Nicole Hu, Wei Dong, Qing Li, Lei Chen
  • Large Language Models (LLMs) have revolutionized a wide range of domains such as natural language processing, computer vision, and multi-modal tasks due to their ability to comprehend context and perform logical reasoning. However, the computational and memory demands of LLMs, particularly during inference, pose significant challenges when scaling them to real-world, long-context, and real-time applications. Key-Value (KV) cache management has emerged as a critical optimization technique for accelerating LLM inference by reducing redundant computations and improving memory utilization. This survey provides a comprehensive overview of KV cache management strategies for LLM acceleration, categorizing them into token-level, model-level, and system-level optimizations. Token-level strategies include KV cache selection, budget allocation, merging, quantization, and low-rank decomposition, while model-level optimizations focus on architectural innovations and attention mechanisms to enhance KV reuse. System-level approaches address memory management, scheduling, and hardware-aware designs to improve efficiency across diverse computing environments. Additionally, the survey provides an overview of both text and multimodal datasets and benchmarks used to evaluate these strategies. By presenting detailed taxonomies and comparative analyses, this work aims to offer useful insights for researchers and practitioners to support the development of efficient and scalable KV cache management techniques, contributing to the practical deployment of LLMs in real-world applications.

PPO readings

a simple blogpost: Preference Tuning LLMs: PPO, DPO, GRPO — A Simple Guide

A Comprehensive Survey of LLM Alignment Techniques: RLHF, RLAIF, PPO, DPO and More

  • [Submitted on 23 Jul 2024]
  • Zhichao Wang, Bin Bi, Shiva Kumar Pentyala, Kiran Ramnath, Sougata Chaudhuri, Shubham Mehrotra, Zixu (James)Zhu, Xiang-Bo Mao, Sitaram Asur, Na (Claire)Cheng
  • With advancements in self-supervised learning, the availability of trillions tokens in a pre-training corpus, instruction fine-tuning, and the development of large Transformers with billions of parameters, large language models (LLMs) are now capable of generating factual and coherent responses to human queries. However, the mixed quality of training data can lead to the generation of undesired responses, presenting a significant challenge. Over the past two years, various methods have been proposed from different perspectives to enhance LLMs, particularly in aligning them with human expectation. Despite these efforts, there has not been a comprehensive survey paper that categorizes and details these approaches. In this work, we aim to address this gap by categorizing these papers into distinct topics and providing detailed explanations of each alignment method, thereby helping readers gain a thorough understanding of the current state of the field.

OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework

  • [Submitted on 20 May 2024 (v1), last revised 24 Nov 2024 (this version, v4)]
  • Jian Hu, Xibin Wu, Zilin Zhu, Xianyu, Weixun Wang, Dehao Zhang, Yu Cao
  • As large language models (LLMs) continue to grow by scaling laws, reinforcement learning from human feedback (RLHF) has gained significant attention due to its outstanding performance. However, unlike pretraining or fine-tuning a single model, scaling reinforcement learning from human feedback (RLHF) for training large language models poses coordination challenges across four models. We present OpenRLHF, an open-source framework enabling efficient RLHF scaling. Unlike existing RLHF frameworks that co-locate four models on the same GPUs, OpenRLHF re-designs scheduling for the models beyond 70B parameters using Ray, vLLM, and DeepSpeed, leveraging improved resource utilization and diverse training approaches. Integrating seamlessly with Hugging Face, OpenRLHF provides an out-of-the-box solution with optimized algorithms and launch scripts, which ensures user-friendliness. OpenRLHF implements RLHF, DPO, rejection sampling, and other alignment techniques. Empowering state-of-the-art LLM development, OpenRLHF’s code is available at \url{this https URL}.

More reading:

Multiple system ML readings

  • [Scheduling] Chunked Prefill (OSDI’24): This is perhaps the most widely adopted scheduling policy in today’s LLM serving systems, which proposes a simple, straightforward idea but works very well. Since it is optimized from Continuous Batching (OSDI’22).
  • [Disaggregated Serving] Splitwise (ISCA’24) / DistServe (OSDI’24): These two papers share a similar idea, separating prefill/decode across different nodes based on stage-specific characteristics. These are also intuitive ideas and are being merged into vLLM.
  • [KV Cache, Tooling] SGLang (NIPS’24): It is a widely used serving framework, an alternative to vLLM. Or, it is more like a programming language tailored to LLM application developers, greatly simplifying the code they need to write. At the core of it is RadixAttention designed for efficient KV cache reuse.
  • [Disaggregated Serving] Helix (ASPLOS’25): This proposes an optimized LLM sharding strategy in a heterogenous cluster to achieve optimal resource allocation.- Disaggregated Serving] ServerlessLLM (OSDI’24): This proposes an efficient live migration of LLM inference on the cloud without losing efficiency.
  • [Scheduling] SJF (NIPS’24): This proposes a statistics-based online algorithm to approximate shortest-job-first scheduling in online LLM inference.
  • [Offloading] FlexGen (ICML’23): This proposes the first offloading strategy specifically for inference systems.

Please click each post's URL shown below to check out its full contents.

17.Extra - BioLLM

  • Team: Extra readings
  • Team: instructor

Summary of Post :

In this session, our readings cover:

Required Readings:

  • https://www.phontron.com/slides/neubig24softwareagents.pdf

More Readings:


Please click each post's URL shown below to check out its full contents.

18.Extra readings - Agent Guardrailing

  • Team: Extra readings
  • Team: instructor

Summary of Post :

In this session, our readings cover:

Required Readings:

  • https://www.phontron.com/slides/neubig24softwareagents.pdf

  • AgentMonitor: A Plug-and-Play Framework for Predictive and Secure Multi-Agent Systems

Chi-Min Chan, Jianxuan Yu, Weize Chen, Chunyang Jiang, Xinyu Liu, Weijie Shi, Zhiyuan Liu, Wei Xue, Yike Guo The rapid advancement of large language models (LLMs) has led to the rise of LLM-based agents. Recent research shows that multi-agent systems (MAS), where each agent plays a specific role, can outperform individual LLMs. However, configuring an MAS for a task remains challenging, with performance only observable post-execution. Inspired by scaling laws in LLM development, we investigate whether MAS performance can be predicted beforehand. We introduce AgentMonitor, a framework that integrates at the agent level to capture inputs and outputs, transforming them into statistics for training a regression model to predict task performance. Additionally, it can further apply real-time corrections to address security risks posed by malicious agents, mitigating negative impacts and enhancing MAS security. Experiments demonstrate that an XGBoost model achieves a Spearman correlation of 0.89 in-domain and 0.58 in more challenging scenarios. Furthermore, using AgentMonitor reduces harmful content by 6.2% and increases helpful content by 1.8% on average, enhancing safety and reliability. Code is available at \url{this https URL}.

  • Identifying the Risks of LM Agents with an LM-Emulated Sandbox

Yangjun Ruan, Honghua Dong, Andrew Wang, Silviu Pitis, Yongchao Zhou, Jimmy Ba, Yann Dubois, Chris J. Maddison, Tatsunori Hashimoto Recent advances in Language Model (LM) agents and tool use, exemplified by applications like ChatGPT Plugins, enable a rich set of capabilities but also amplify potential risks - such as leaking private data or causing financial losses. Identifying these risks is labor-intensive, necessitating implementing the tools, setting up the environment for each test scenario manually, and finding risky cases. As tools and agents become more complex, the high cost of testing these agents will make it increasingly difficult to find high-stakes, long-tailed risks. To address these challenges, we introduce ToolEmu: a framework that uses an LM to emulate tool execution and enables the testing of LM agents against a diverse range of tools and scenarios, without manual instantiation. Alongside the emulator, we develop an LM-based automatic safety evaluator that examines agent failures and quantifies associated risks. We test both the tool emulator and evaluator through human evaluation and find that 68.8% of failures identified with ToolEmu would be valid real-world agent failures. Using our curated initial benchmark consisting of 36 high-stakes tools and 144 test cases, we provide a quantitative risk analysis of current LM agents and identify numerous failures with potentially severe outcomes. Notably, even the safest LM agent exhibits such failures 23.9% of the time according to our evaluator, underscoring the need to develop safer LM agents for real-world deployment.

  • SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Model [Submitted on 28 Jan 2025 (v1), last revised 23 Feb 2025 (this version, v2)] Xun Liang, Simin Niu, Zhiyu Li, Sensen Zhang, Hanyu Wang, Feiyu Xiong, Jason Zhaoxin Fan, Bo Tang, Shichao Song, Mengwei Wang, Jiawei Yang The indexing-retrieval-generation paradigm of retrieval-augmented generation (RAG) has been highly successful in solving knowledge-intensive tasks by integrating external knowledge into large language models (LLMs). However, the incorporation of external and unverified knowledge increases the vulnerability of LLMs because attackers can perform attack tasks by manipulating knowledge. In this paper, we introduce a benchmark named SafeRAG designed to evaluate the RAG security. First, we classify attack tasks into silver noise, inter-context conflict, soft ad, and white Denial-of-Service. Next, we construct RAG security evaluation dataset (i.e., SafeRAG dataset) primarily manually for each task. We then utilize the SafeRAG dataset to simulate various attack scenarios that RAG may encounter. Experiments conducted on 14 representative RAG components demonstrate that RAG exhibits significant vulnerability to all attack tasks and even the most apparent attack task can easily bypass existing retrievers, filters, or advanced LLMs, resulting in the degradation of RAG service quality. Code is available at: this https URL.

  • Building Safe GenAI Applications: An End-to-End Overview of Red Teaming for Large Language Models

[Submitted on 3 Mar 2025 (v1), last revised 5 Mar 2025 (this version, v2)] Alberto Purpura, Sahil Wadhwa, Jesse Zymet, Akshay Gupta, Andy Luo, Melissa Kazemi Rad, Swapnil Shinde, Mohammad Shahed Sorower The rapid growth of Large Language Models (LLMs) presents significant privacy, security, and ethical concerns. While much research has proposed methods for defending LLM systems against misuse by malicious actors, researchers have recently complemented these efforts with an offensive approach that involves red teaming, i.e., proactively attacking LLMs with the purpose of identifying their vulnerabilities. This paper provides a concise and practical overview of the LLM red teaming literature, structured so as to describe a multi-component system end-to-end. To motivate red teaming we survey the initial safety needs of some high-profile LLMs, and then dive into the different components of a red teaming system as well as software packages for implementing them. We cover various attack methods, strategies for attack-success evaluation, metrics for assessing experiment outcomes, as well as a host of other considerations. Our survey will be useful for any reader who wants to rapidly obtain a grasp of the major red teaming concepts for their own use in practical applications.

  • UDora: A Unified Red Teaming Framework against LLM Agents by Dynamically Hijacking Their Own Reasoning

[Submitted on 28 Feb 2025] Jiawei Zhang, Shuang Yang, Bo Li Large Language Model (LLM) agents equipped with external tools have become increasingly powerful for handling complex tasks such as web shopping, automated email replies, and financial trading. However, these advancements also amplify the risks of adversarial attacks, particularly when LLM agents can access sensitive external functionalities. Moreover, because LLM agents engage in extensive reasoning or planning before executing final actions, manipulating them into performing targeted malicious actions or invoking specific tools remains a significant challenge. Consequently, directly embedding adversarial strings in malicious instructions or injecting malicious prompts into tool interactions has become less effective against modern LLM agents. In this work, we present UDora, a unified red teaming framework designed for LLM Agents that dynamically leverages the agent’s own reasoning processes to compel it toward malicious behavior. Specifically, UDora first samples the model’s reasoning for the given task, then automatically identifies multiple optimal positions within these reasoning traces to insert targeted perturbations. Subsequently, it uses the modified reasoning as the objective to optimize the adversarial strings. By iteratively applying this process, the LLM agent will then be induced to undertake designated malicious actions or to invoke specific malicious tools. Our approach demonstrates superior effectiveness compared to existing methods across three LLM agent datasets.

  • Safeguarding Large Language Models: A Survey [Submitted on 3 Jun 2024] Yi Dong, Ronghui Mu, Yanghao Zhang, Siqi Sun, Tianle Zhang, Changshun Wu, Gaojie Jin, Yi Qi, Jinwei Hu, Jie Meng, Saddek Bensalem, Xiaowei Huang In the burgeoning field of Large Language Models (LLMs), developing a robust safety mechanism, colloquially known as “safeguards” or “guardrails”, has become imperative to ensure the ethical use of LLMs within prescribed boundaries. This article provides a systematic literature review on the current status of this critical mechanism. It discusses its major challenges and how it can be enhanced into a comprehensive mechanism dealing with ethical issues in various contexts. First, the paper elucidates the current landscape of safeguarding mechanisms that major LLM service providers and the open-source community employ. This is followed by the techniques to evaluate, analyze, and enhance some (un)desirable properties that a guardrail might want to enforce, such as hallucinations, fairness, privacy, and so on. Based on them, we review techniques to circumvent these controls (i.e., attacks), to defend the attacks, and to reinforce the guardrails. While the techniques mentioned above represent the current status and the active research trends, we also discuss several challenges that cannot be easily dealt with by the methods and present our vision on how to implement a comprehensive guardrail through the full consideration of multi-disciplinary approach, neural-symbolic method, and systems development lifecycle.

More Readings:


Please click each post's URL shown below to check out its full contents.

19.Agent - In Healthcare

  • Team: Health AI Agents
  • Team: TA
Agent

Summary of Post :

In this session, our readings cover:

Required Readings:

The rise of agentic AI teammates in medicine

  • Perspectives Digital medicine Volume 405, Issue 10477 vp457 February 08, 2025
  • James Zou jamesz@stanford.edu ∙ Eric J Topol
  • Medicine is in the dawn of a fundamental shift from using artificial intelligence (AI) as tools to deploying AI as agents. When used as a tool, AI is passive and reactive. Even powerful medical AI foundation models today remain tools that depend on human users to provide input and context, interpret their output, and take follow-up steps. To fully unlock AI’s potential in medicine, clinicians need to make the key conceptual shift from using AI as sophisticated calculators to embracing AI as health-care teammates.

From Medprompt to o1: Exploration of Run-Time Strategies for Medical Challenge Problems and Beyond

  • Harsha Nori, Naoto Usuyama, Nicholas King, Scott Mayer McKinney, Xavier Fernandes, Sheng Zhang, Eric Horvitz
  • Run-time steering strategies like Medprompt are valuable for guiding large language models (LLMs) to top performance on challenging tasks. Medprompt demonstrates that a general LLM can be focused to deliver state-of-the-art performance on specialized domains like medicine by using a prompt to elicit a run-time strategy involving chain of thought reasoning and ensembling. OpenAI’s o1-preview model represents a new paradigm, where a model is designed to do run-time reasoning before generating final responses. We seek to understand the behavior of o1-preview on a diverse set of medical challenge problem benchmarks. Following on the Medprompt study with GPT-4, we systematically evaluate the o1-preview model across various medical benchmarks. Notably, even without prompting techniques, o1-preview largely outperforms the GPT-4 series with Medprompt. We further systematically study the efficacy of classic prompt engineering strategies, as represented by Medprompt, within the new paradigm of reasoning models. We found that few-shot prompting hinders o1’s performance, suggesting that in-context learning may no longer be an effective steering approach for reasoning-native models. While ensembling remains viable, it is resource-intensive and requires careful cost-performance optimization. Our cost and accuracy analysis across run-time strategies reveals a Pareto frontier, with GPT-4o representing a more affordable option and o1-preview achieving state-of-the-art performance at higher cost. Although o1-preview offers top performance, GPT-4o with steering strategies like Medprompt retains value in specific contexts. Moreover, we note that the o1-preview model has reached near-saturation on many existing medical benchmarks, underscoring the need for new, challenging benchmarks. We close with reflections on general directions for inference-time computation with LLMs.

A Survey on Medical Large Language Models: Technology, Application, Trustworthiness, and Future Directions

  • Lei Liu, Xiaoyan Yang, Junchi Lei, Yue Shen, Jian Wang, Peng Wei, Zhixuan Chu, Zhan Qin, Kui Ren
  • With the advent of Large Language Models (LLMs), medical artificial intelligence (AI) has experienced substantial technological progress and paradigm shifts, highlighting the potential of LLMs to streamline healthcare delivery and improve patient outcomes. Considering this rapid technical progress, in this survey, we trace the recent advances of Medical Large Language Models (Med-LLMs), including the background, key findings, and mainstream techniques, especially for the evolution from general-purpose models to medical-specialized applications. Firstly, we delve into the foundational technology of Med-LLMs, indicating how general models can be progressively adapted and refined for the complicated medical tasks. Secondly, the wide-ranging applications of Med-LLMs are investigated across various healthcare domains, as well as an up-to-date review of existing Med-LLMs. The transformative impact of these models on daily medical practice is evident through their ability to assist clinicians, educators, and patients. Recognizing the importance of responsible innovation, we discuss the challenges associated with ensuring fairness, accountability, privacy, and robustness. Ethical considerations, rigorous evaluation methodologies, and the establishment of regulatory frameworks are crucial for building trustworthiness in the real-world system. We emphasize the need for ongoing scrutiny and development to maintain high standards of safety and reliability. Finally, we anticipate possible future trajectories for Med-LLMs, identifying key avenues for prudent expansion. By consolidating these insights, our review aims to provide professionals and researchers with a thorough understanding of the strengths and limitations of Med-LLMs, fostering a balanced and ethical approach to their integration into the healthcare ecosystem.

A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethics

  • Kai He, Rui Mao, Qika Lin, Yucheng Ruan, Xiang Lan, Mengling Feng, Erik Cambria
  • The utilization of large language models (LLMs) in the Healthcare domain has generated both excitement and concern due to their ability to effectively respond to freetext queries with certain professional knowledge. This survey outlines the capabilities of the currently developed LLMs for Healthcare and explicates their development process, with the aim of providing an overview of the development roadmap from traditional Pretrained Language Models (PLMs) to LLMs. Specifically, we first explore the potential of LLMs to enhance the efficiency and effectiveness of various Healthcare applications highlighting both the strengths and limitations. Secondly, we conduct a comparison between the previous PLMs and the latest LLMs, as well as comparing various LLMs with each other. Then we summarize related Healthcare training data, training methods, optimization strategies, and usage. Finally, the unique concerns associated with deploying LLMs in Healthcare settings are investigated, particularly regarding fairness, accountability, transparency and ethics. Our survey provide a comprehensive investigation from perspectives of both computer science and Healthcare specialty. Besides the discussion about Healthcare concerns, we supports the computer science community by compiling a collection of open source resources, such as accessible datasets, the latest methodologies, code implementations, and evaluation benchmarks in the Github. Summarily, we contend that a significant paradigm shift is underway, transitioning from PLMs to LLMs. This shift encompasses a move from discriminative AI approaches to generative AI approaches, as well as a shift from model-centered methodologies to data-centered methodologies. Also, we determine that the biggest obstacle of using LLMs in Healthcare are fairness, accountability, transparency and ethics.

More Readings:

MEDEC: A Benchmark for Medical Error Detection and Correction in Clinical Notes

  • Asma Ben Abacha, Wen-wai Yim, Yujuan Fu, Zhaoyi Sun, Meliha Yetisgen, Fei Xia, Thomas Lin
  • [Submitted on 26 Dec 2024 (v1), last revised 2 Jan 2025 (this version, v2)]
  • Several studies showed that Large Language Models (LLMs) can answer medical questions correctly, even outperforming the average human score in some medical exams. However, to our knowledge, no study has been conducted to assess the ability of language models to validate existing or generated medical text for correctness and consistency. In this paper, we introduce MEDEC (this https URL), the first publicly available benchmark for medical error detection and correction in clinical notes, covering five types of errors (Diagnosis, Management, Treatment, Pharmacotherapy, and Causal Organism). MEDEC consists of 3,848 clinical texts, including 488 clinical notes from three US hospital systems that were not previously seen by any LLM. The dataset has been used for the MEDIQA-CORR shared task to evaluate seventeen participating systems [Ben Abacha et al., 2024]. In this paper, we describe the data creation methods and we evaluate recent LLMs (e.g., o1-preview, GPT-4, Claude 3.5 Sonnet, and Gemini 2.0 Flash) for the tasks of detecting and correcting medical errors requiring both medical knowledge and reasoning capabilities. We also conducted a comparative study where two medical doctors performed the same task on the MEDEC test set. The results showed that MEDEC is a sufficiently challenging benchmark to assess the ability of models to validate existing or generated notes and to correct medical errors. We also found that although recent LLMs have a good performance in error detection and correction, they are still outperformed by medical doctors in these tasks. We discuss the potential factors behind this gap, the insights from our experiments, the limitations of current evaluation metrics, and share potential pointers for future research.

A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery

  • Yu Zhang, Xiusi Chen, Bowen Jin, Sheng Wang, Shuiwang Ji, Wei Wang, Jiawei Han
  • In many scientific fields, large language models (LLMs) have revolutionized the way text and other modalities of data (e.g., molecules and proteins) are handled, achieving superior performance in various applications and augmenting the scientific discovery process. Nevertheless, previous surveys on scientific LLMs often concentrate on one or two fields or a single modality. In this paper, we aim to provide a more holistic view of the research landscape by unveiling cross-field and cross-modal connections between scientific LLMs regarding their architectures and pre-training techniques. To this end, we comprehensively survey over 260 scientific LLMs, discuss their commonalities and differences, as well as summarize pre-training datasets and evaluation tasks for each field and modality. Moreover, we investigate how LLMs have been deployed to benefit scientific discovery. Resources related to this survey are available at this https URL.

Please click each post's URL shown below to check out its full contents.

20.Platform - long context vs RAG + Hallucination

  • Team: team-2
RAG LongContext

Summary of Post :

In this session, our readings cover:

Required Readings:

Importing Phantoms: Measuring LLM Package Hallucination Vulnerabilities

  • [Submitted on 31 Jan 2025]
  • Arjun Krishna, Erick Galinkin, Leon Derczynski, Jeffrey Martin Large Language Models (LLMs) have become an essential tool in the programmer’s toolkit, but their tendency to hallucinate code can be used by malicious actors to introduce vulnerabilities to broad swathes of the software supply chain. In this work, we analyze package hallucination behaviour in LLMs across popular programming languages examining both existing package references and fictional dependencies. By analyzing this package hallucination behaviour we find potential attacks and suggest defensive strategies to defend against these attacks. We discover that package hallucination rate is predicated not only on model choice, but also programming language, model size, and specificity of the coding task request. The Pareto optimality boundary between code generation performance and package hallucination is sparsely populated, suggesting that coding models are not being optimized for secure code. Additionally, we find an inverse correlation between package hallucination rate and the HumanEval coding benchmark, offering a heuristic for evaluating the propensity of a model to hallucinate packages. Our metrics, findings and analyses provide a base for future models, securing AI-assisted software development workflows against package supply chain attacks.

YaRN: Efficient Context Window Extension of Large Language Models

  • [Submitted on 31 Aug 2023 (v1), last revised 1 Nov 2023 (this version, v2)]
  • Bowen Peng, Jeffrey Quesnelle, Honglu Fan, Enrico Shippole
  • Rotary Position Embeddings (RoPE) have been shown to effectively encode positional information in transformer-based language models. However, these models fail to generalize past the sequence length they were trained on. We present YaRN (Yet another RoPE extensioN method), a compute-efficient method to extend the context window of such models, requiring 10x less tokens and 2.5x less training steps than previous methods. Using YaRN, we show that LLaMA models can effectively utilize and extrapolate to context lengths much longer than their original pre-training would allow, while also surpassing previous the state-of-the-art at context window extension. In addition, we demonstrate that YaRN exhibits the capability to extrapolate beyond the limited context of a fine-tuning dataset. The models fine-tuned using YaRN has been made available and reproduced online up to 128k context length at this https URL

Long Context vs. RAG for LLMs: An Evaluation and Revisits

  • [Submitted on 27 Dec 2024]
  • https://arxiv.org/abs/2501.01880
  • Xinze Li, Yixin Cao, Yubo Ma, Aixin Sun
  • Extending context windows (i.e., Long Context, LC) and using retrievers to selectively access relevant information (i.e., Retrieval-Augmented Generation, RAG) are the two main strategies to enable LLMs to incorporate extremely long external contexts. This paper revisits recent studies on this topic, highlighting their key insights and discrepancies. We then provide a more comprehensive evaluation by filtering out questions answerable without external context, identifying the most effective retrieval methods, and expanding the datasets. We show that LC generally outperforms RAG in question-answering benchmarks, especially for Wikipedia-based questions. Summarization-based retrieval performs comparably to LC, while chunk-based retrieval lags behind. However, RAG has advantages in dialogue-based and general question queries. These insights underscore the trade-offs between RAG and LC strategies, offering guidance for future optimization of LLMs with external knowledge sources. We also provide an in-depth discussion on this topic, highlighting the overlooked importance of context relevance in existing studies.

More reading:

LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference

  • [Submitted on 19 Jul 2024]
  • Qichen Fu, Minsik Cho, Thomas Merth, Sachin Mehta, Mohammad Rastegari, Mahyar Najibi
  • The inference of transformer-based large language models consists of two sequential stages: 1) a prefilling stage to compute the KV cache of prompts and generate the first token, and 2) a decoding stage to generate subsequent tokens. For long prompts, the KV cache must be computed for all tokens during the prefilling stage, which can significantly increase the time needed to generate the first token. Consequently, the prefilling stage may become a bottleneck in the generation process. An open question remains whether all prompt tokens are essential for generating the first token. To answer this, we introduce a novel method, LazyLLM, that selectively computes the KV for tokens important for the next token prediction in both the prefilling and decoding stages. Contrary to static pruning approaches that prune the prompt at once, LazyLLM allows language models to dynamically select different subsets of tokens from the context in different generation steps, even though they might be pruned in previous steps. Extensive experiments on standard datasets across various tasks demonstrate that LazyLLM is a generic method that can be seamlessly integrated with existing language models to significantly accelerate the generation without fine-tuning. For instance, in the multi-document question-answering task, LazyLLM accelerates the prefilling stage of the LLama 2 7B model by 2.34x while maintaining accuracy.

Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention

  • Submitted on 10 Apr 2024 (v1), last revised 9 Aug 2024 (this version, v2)]
  • Tsendsuren Munkhdalai, Manaal Faruqui, Siddharth Gopal
  • This work introduces an efficient method to scale Transformer-based Large Language Models (LLMs) to infinitely long inputs with bounded memory and computation. A key component in our proposed approach is a new attention technique dubbed Infini-attention. The Infini-attention incorporates a compressive memory into the vanilla attention mechanism and builds in both masked local attention and long-term linear attention mechanisms in a single Transformer block. We demonstrate the effectiveness of our approach on long-context language modeling benchmarks, 1M sequence length passkey context block retrieval and 500K length book summarization tasks with 1B and 8B LLMs. Our approach introduces minimal bounded memory parameters and enables fast streaming inference for LLMs.

Don’t Do RAG: When Cache-Augmented Generation is All You Need for Knowledge Tasks

  • [Submitted on 20 Dec 2024]
  • Brian J Chan, Chao-Ting Chen, Jui-Hung Cheng, Hen-Hsen Huang
  • Retrieval-augmented generation (RAG) has gained traction as a powerful approach for enhancing language models by integrating external knowledge sources. However, RAG introduces challenges such as retrieval latency, potential errors in document selection, and increased system complexity. With the advent of large language models (LLMs) featuring significantly extended context windows, this paper proposes an alternative paradigm, cache-augmented generation (CAG) that bypasses real-time retrieval. Our method involves preloading all relevant resources, especially when the documents or knowledge for retrieval are of a limited and manageable size, into the LLM’s extended context and caching its runtime parameters. During inference, the model utilizes these preloaded parameters to answer queries without additional retrieval steps. Comparative analyses reveal that CAG eliminates retrieval latency and minimizes retrieval errors while maintaining context relevance. Performance evaluations across multiple benchmarks highlight scenarios where long-context LLMs either outperform or complement traditional RAG pipelines. These findings suggest that, for certain applications, particularly those with a constrained knowledge base, CAG provide a streamlined and efficient alternative to RAG, achieving comparable or superior results with reduced complexity.

Please click each post's URL shown below to check out its full contents.

21.Agent - Planning / World Model

  • Team: team-3
Planning

Summary of Post :

In this session, our readings cover:

Required Readings:

AI Planning: A Primer and Survey (Preliminary Report)

  • Dillon Z. Chen, Pulkit Verma, Siddharth Srivastava, Michael Katz, Sylvie Thiébaux
  • [Submitted on 7 Dec 2024]
  • Automated decision-making is a fundamental topic that spans multiple sub-disciplines in AI: reinforcement learning (RL), AI planning (AP), foundation models, and operations research, among others. Despite recent efforts to ``bridge the gaps’’ between these communities, there remain many insights that have not yet transcended the boundaries. Our goal in this paper is to provide a brief and non-exhaustive primer on ideas well-known in AP, but less so in other sub-disciplines. We do so by introducing the classical AP problem and representation, and extensions that handle uncertainty and time through the Markov Decision Process formalism. Next, we survey state-of-the-art techniques and ideas for solving AP problems, focusing on their ability to exploit problem structure. Lastly, we cover subfields within AP for learning structure from unstructured inputs and learning to generalise to unseen scenarios and situations.

Reasoning with Language Model is Planning with World Model

  • [Submitted on 24 May 2023 (v1), last revised 23 Oct 2023 (this version, v2)]
  • Shibo Hao, Yi Gu, Haodi Ma, Joshua Jiahua Hong, Zhen Wang, Daisy Zhe Wang, Zhiting Hu
  • Large language models (LLMs) have shown remarkable reasoning capabilities, especially when prompted to generate intermediate reasoning steps (e.g., Chain-of-Thought, CoT). However, LLMs can still struggle with problems that are easy for humans, such as generating action plans for executing tasks in a given environment, or performing complex math, logical, and commonsense reasoning. The deficiency stems from the key fact that LLMs lack an internal world model to predict the world state (e.g., environment status, intermediate variable values) and simulate long-term outcomes of actions. This prevents LLMs from performing deliberate planning akin to human brains, which involves exploring alternative reasoning paths, anticipating future states and rewards, and iteratively refining existing reasoning steps. To overcome the limitations, we propose a new LLM reasoning framework, Reasoning via Planning (RAP). RAP repurposes the LLM as both a world model and a reasoning agent, and incorporates a principled planning algorithm (based on Monto Carlo Tree Search) for strategic exploration in the vast reasoning space. During reasoning, the LLM (as agent) incrementally builds a reasoning tree under the guidance of the LLM (as world model) and task-specific rewards, and obtains a high-reward reasoning path efficiently with a proper balance between exploration vs. exploitation. We apply RAP to a variety of challenging reasoning problems including plan generation, math reasoning, and logical inference. Empirical results on these tasks demonstrate the superiority of RAP over various strong baselines, including CoT and least-to-most prompting with self-consistency. RAP on LLAMA-33B surpasses CoT on GPT-4 with 33% relative improvement in a plan generation setting.

Agent Planning with World Knowledge Model

  • Shuofei Qiao, Runnan Fang, Ningyu Zhang, Yuqi Zhu, Xiang Chen, Shumin Deng, Yong Jiang, Pengjun Xie, Fei Huang, Huajun Chen
  • [Submitted on 23 May 2024 (v1), last revised 3 Jan 2025 (this version, v4)]
  • NeurIPS 2024
  • Recent endeavors towards directly using large language models (LLMs) as agent models to execute interactive planning tasks have shown commendable results. Despite their achievements, however, they still struggle with brainless trial-and-error in global planning and generating hallucinatory actions in local planning due to their poor understanding of the ``real’’ physical world. Imitating humans’ mental world knowledge model which provides global prior knowledge before the task and maintains local dynamic knowledge during the task, in this paper, we introduce parametric World Knowledge Model (WKM) to facilitate agent planning. Concretely, we steer the agent model to self-synthesize knowledge from both expert and sampled trajectories. Then we develop WKM, providing prior task knowledge to guide the global planning and dynamic state knowledge to assist the local planning. Experimental results on three complex real-world simulated datasets with three state-of-the-art open-source LLMs, Mistral-7B, Gemma-7B, and Llama-3-8B, demonstrate that our method can achieve superior performance compared to various strong baselines. Besides, we analyze to illustrate that our WKM can effectively alleviate the blind trial-and-error and hallucinatory action issues, providing strong support for the agent’s understanding of the world. Other interesting findings include: 1) our instance-level task knowledge can generalize better to unseen tasks, 2) weak WKM can guide strong agent model planning, and 3) unified WKM training has promising potential for further development. The code is available at this https URL. Comments: NeurIPS 2024

More Readings:

O1 Replication Journey: A Strategic Progress Report – Part 1

  • [Submitted on 8 Oct 2024]
  • URL
  • Yiwei Qin, Xuefeng Li, Haoyang Zou, Yixiu Liu, Shijie Xia, Zhen Huang, Yixin Ye, Weizhe Yuan, Hector Liu, Yuanzhi Li, Pengfei Liu
  • This paper introduces a pioneering approach to artificial intelligence research, embodied in our O1 Replication Journey. In response to the announcement of OpenAI’s groundbreaking O1 model, we embark on a transparent, real-time exploration to replicate its capabilities while reimagining the process of conducting and communicating AI research. Our methodology addresses critical challenges in modern AI research, including the insularity of prolonged team-based projects, delayed information sharing, and the lack of recognition for diverse contributions. By providing comprehensive, real-time documentation of our replication efforts, including both successes and failures, we aim to foster open science, accelerate collective advancement, and lay the groundwork for AI-driven scientific discovery. Our research progress report diverges significantly from traditional research papers, offering continuous updates, full process transparency, and active community engagement throughout the research journey. Technologically, we proposed the journey learning paradigm, which encourages models to learn not just shortcuts, but the complete exploration process, including trial and error, reflection, and backtracking. With only 327 training samples and without any additional tricks, journey learning outperformed conventional supervised learning by over 8\% on the MATH dataset, demonstrating its extremely powerful potential. We believe this to be the most crucial component of O1 technology that we have successfully decoded. We share valuable resources including technical hypotheses and insights, cognitive exploration maps, custom-developed tools, etc at this https URL.

Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective

  • [Submitted on 18 Dec 2024]
  • https://arxiv.org/abs/2412.14135
  • Zhiyuan Zeng, Qinyuan Cheng, Zhangyue Yin, Bo Wang, Shimin Li, Yunhua Zhou, Qipeng Guo, Xuanjing Huang, Xipeng Qiu
  • OpenAI o1 represents a significant milestone in Artificial Inteiligence, which achieves expert-level performances on many challanging tasks that require strong reasoning this http URL has claimed that the main techinique behinds o1 is the reinforcement learining. Recent works use alternative approaches like knowledge distillation to imitate o1’s reasoning style, but their effectiveness is limited by the capability ceiling of the teacher model. Therefore, this paper analyzes the roadmap to achieving o1 from the perspective of reinforcement learning, focusing on four key components: policy initialization, reward design, search, and learning. Policy initialization enables models to develop human-like reasoning behaviors, equipping them with the ability to effectively explore solution spaces for complex problems. Reward design provides dense and effective signals via reward shaping or reward modeling, which is the guidance for both search and learning. Search plays a crucial role in generating high-quality solutions during both training and testing phases, which can produce better solutions with more computation. Learning utilizes the data generated by search for improving policy, which can achieve the better performance with more parameters and more searched data. Existing open-source projects that attempt to reproduce o1 can be seem as a part or a variant of our roadmap. Collectively, these components underscore how learning and search drive o1’s advancement, making meaningful contributions to the development of LLM.

Improving Transformer World Models for Data-Efficient RL

  • [Submitted on 3 Feb 2025]
  • Antoine Dedieu, Joseph Ortiz, Xinghua Lou, Carter Wendelken, Wolfgang Lehrach, J Swaroop Guntupalli, Miguel Lazaro-Gredilla, Kevin Patrick Murphy
  • We present an approach to model-based RL that achieves a new state of the art performance on the challenging Craftax-classic benchmark, an open-world 2D survival game that requires agents to exhibit a wide range of general abilities – such as strong generalization, deep exploration, and long-term reasoning. With a series of careful design choices aimed at improving sample efficiency, our MBRL algorithm achieves a reward of 67.4% after only 1M environment steps, significantly outperforming DreamerV3, which achieves 53.2%, and, for the first time, exceeds human performance of 65.0%. Our method starts by constructing a SOTA model-free baseline, using a novel policy architecture that combines CNNs and RNNs. We then add three improvements to the standard MBRL setup: (a) “Dyna with warmup”, which trains the policy on real and imaginary data, (b) “nearest neighbor tokenizer” on image patches, which improves the scheme to create the transformer world model (TWM) inputs, and (c) “block teacher forcing”, which allows the TWM to reason jointly about the future tokens of the next timestep.

Please click each post's URL shown below to check out its full contents.

22.Agent Safety / More Autonomous Agents

  • Team: team-4
Safety Agent

Summary of Post :

In this session, our readings cover:

Required Readings:

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents

  • Maksym Andriushchenko, Alexandra Souly, Mateusz Dziemian, Derek Duenas, Maxwell Lin, Justin Wang, Dan Hendrycks, Andy Zou, Zico Kolter, Matt Fredrikson, Eric Winsor, Jerome Wynne, Yarin Gal, Xander Davies
  • [Submitted on 11 Oct 2024 (v1), last revised 14 Oct 2024 (this version, v2)]
  • The robustness of LLMs to jailbreak attacks, where users design prompts to circumvent safety measures and misuse model capabilities, has been studied primarily for LLMs acting as simple chatbots. Meanwhile, LLM agents – which use external tools and can execute multi-stage tasks – may pose a greater risk if misused, but their robustness remains underexplored. To facilitate research on LLM agent misuse, we propose a new benchmark called AgentHarm. The benchmark includes a diverse set of 110 explicitly malicious agent tasks (440 with augmentations), covering 11 harm categories including fraud, cybercrime, and harassment. In addition to measuring whether models refuse harmful agentic requests, scoring well on AgentHarm requires jailbroken agents to maintain their capabilities following an attack to complete a multi-step task. We evaluate a range of leading LLMs, and find (1) leading LLMs are surprisingly compliant with malicious agent requests without jailbreaking, (2) simple universal jailbreak templates can be adapted to effectively jailbreak agents, and (3) these jailbreaks enable coherent and malicious multi-step agent behavior and retain model capabilities. To enable simple and reliable evaluation of attacks and defenses for LLM-based agents, we publicly release AgentHarm at this https URL.

[Submitted on 28 Jul 2024] The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies Feng He, Tianqing Zhu, Dayong Ye, Bo Liu, Wanlei Zhou, Philip S. Yu Inspired by the rapid development of Large Language Models (LLMs), LLM agents have evolved to perform complex tasks. LLM agents are now extensively applied across various domains, handling vast amounts of data to interact with humans and execute tasks. The widespread applications of LLM agents demonstrate their significant commercial value; however, they also expose security and privacy vulnerabilities. At the current stage, comprehensive research on the security and privacy of LLM agents is highly needed. This survey aims to provide a comprehensive overview of the newly emerged privacy and security issues faced by LLM agents. We begin by introducing the fundamental knowledge of LLM agents, followed by a categorization and analysis of the threats. We then discuss the impacts of these threats on humans, environment, and other agents. Subsequently, we review existing defensive strategies, and finally explore future trends. Additionally, the survey incorporates diverse case studies to facilitate a more accessible understanding. By highlighting these critical security and privacy issues, the survey seeks to stimulate future research towards enhancing the security and privacy of LLM agents, thereby increasing their reliability and trustworthiness in future applications.

More Readings:

Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

  • Yongshuo Zong, Ondrej Bohdal, Tingyang Yu, Yongxin Yang, Timothy Hospedales
  • [Submitted on 3 Feb 2024 (v1), last revised 17 Jun 2024 (this version, v2)]
  • Current vision large language models (VLLMs) exhibit remarkable capabilities yet are prone to generate harmful content and are vulnerable to even the simplest jailbreaking attacks. Our initial analysis finds that this is due to the presence of harmful data during vision-language instruction fine-tuning, and that VLLM fine-tuning can cause forgetting of safety alignment previously learned by the underpinning LLM. To address this issue, we first curate a vision-language safe instruction-following dataset VLGuard covering various harmful categories. Our experiments demonstrate that integrating this dataset into standard vision-language fine-tuning or utilizing it for post-hoc fine-tuning effectively safety aligns VLLMs. This alignment is achieved with minimal impact on, or even enhancement of, the models’ helpfulness. The versatility of our safety fine-tuning dataset makes it a valuable resource for safety-testing existing VLLMs, training new models or safeguarding pre-trained VLLMs. Empirical results demonstrate that fine-tuned VLLMs effectively reject unsafe instructions and substantially reduce the success rates of several black-box adversarial attacks, which approach zero in many cases. The code and dataset are available at this https URL.

Unique Security and Privacy Threats of Large Language Model: A Comprehensive Survey

  • [Submitted on 12 Jun 2024 (v1), last revised 18 Jun 2024 (this version, v2)]
  • Shang Wang, Tianqing Zhu, Bo Liu, Ming Ding, Xu Guo, Dayong Ye, Wanlei Zhou, Philip S. Yu
  • With the rapid development of artificial intelligence, large language models (LLMs) have made remarkable advancements in natural language processing. These models are trained on vast datasets to exhibit powerful language understanding and generation capabilities across various applications, including machine translation, chatbots, and agents. However, LLMs have revealed a variety of privacy and security issues throughout their life cycle, drawing significant academic and industrial attention. Moreover, the risks faced by LLMs differ significantly from those encountered by traditional language models. Given that current surveys lack a clear taxonomy of unique threat models across diverse scenarios, we emphasize the unique privacy and security threats associated with five specific scenarios: pre-training, fine-tuning, retrieval-augmented generation systems, deployment, and LLM-based agents. Addressing the characteristics of each risk, this survey outlines potential threats and countermeasures. Research on attack and defense situations can offer feasible research directions, enabling more areas to benefit from LLMs.

Large Language Model Safety: A Holistic Survey

  • Dan Shi, Tianhao Shen, Yufei Huang, Zhigen Li, Yongqi Leng, Renren Jin, Chuang Liu, Xinwei Wu, Zishan Guo, Linhao Yu, Ling Shi, Bojian Jiang, Deyi Xiong
  • [Submitted on 23 Dec 2024]
  • The rapid development and deployment of large language models (LLMs) have introduced a new frontier in artificial intelligence, marked by unprecedented capabilities in natural language understanding and generation. However, the increasing integration of these models into critical applications raises substantial safety concerns, necessitating a thorough examination of their potential risks and associated mitigation strategies. This survey provides a comprehensive overview of the current landscape of LLM safety, covering four major categories: value misalignment, robustness to adversarial attacks, misuse, and autonomous AI risks. In addition to the comprehensive review of the mitigation methodologies and evaluation resources on these four aspects, we further explore four topics related to LLM safety: the safety implications of LLM agents, the role of interpretability in enhancing LLM safety, the technology roadmaps proposed and abided by a list of AI companies and institutes for LLM safety, and AI governance aimed at LLM safety with discussions on international cooperation, policy proposals, and prospective regulatory directions. Our findings underscore the necessity for a proactive, multifaceted approach to LLM safety, emphasizing the integration of technical solutions, ethical considerations, and robust governance frameworks. This survey is intended to serve as a foundational resource for academy researchers, industry practitioners, and policymakers, offering insights into the challenges and opportunities associated with the safe integration of LLMs into society. Ultimately, it seeks to contribute to the safe and beneficial development of LLMs, aligning with the overarching goal of harnessing AI for societal advancement and well-being. A curated list of related papers has been publicly available at this https URL.

MobileSafetyBench: Evaluating Safety of Autonomous Agents in Mobile Device Control

  • https://arxiv.org/pdf/2410.17520
  • [Submitted on 23 Oct 2024 (v1), last revised 10 Dec 2024 (this version, v2)]
  • Juyong Lee, Dongyoon Hahm, June Suk Choi, W. Bradley Knox, Kimin Lee
  • Autonomous agents powered by large language models (LLMs) show promising potential in assistive tasks across various domains, including mobile device control. As these agents interact directly with personal information and device settings, ensuring their safe and reliable behavior is crucial to prevent undesirable outcomes. However, no benchmark exists for standardized evaluation of the safety of mobile device-control agents. In this work, we introduce MobileSafetyBench, a benchmark designed to evaluate the safety of device-control agents within a realistic mobile environment based on Android emulators. We develop a diverse set of tasks involving interactions with various mobile applications, including messaging and banking applications, challenging agents with managing risks encompassing misuse and negative side effects. These tasks include tests to evaluate the safety of agents in daily scenarios as well as their robustness against indirect prompt injection attacks. Our experiments demonstrate that baseline agents, based on state-of-the-art LLMs, often fail to effectively prevent harm while performing the tasks. To mitigate these safety concerns, we propose a prompting method that encourages agents to prioritize safety considerations. While this method shows promise in promoting safer behaviors, there is still considerable room for improvement to fully earn user trust. This highlights the urgent need for continued research to develop more robust safety mechanisms in mobile environments. We open-source our benchmark at: this https URL.

Privacy-Preserving Large Language Models: Mechanisms, Applications, and Future Directions

  • Guoshenghui Zhao, Eric Song
  • [Submitted on 9 Dec 2024]
  • The rapid advancement of large language models (LLMs) has revolutionized natural language processing, enabling applications in diverse domains such as healthcare, finance and education. However, the growing reliance on extensive data for training and inference has raised significant privacy concerns, ranging from data leakage to adversarial attacks. This survey comprehensively explores the landscape of privacy-preserving mechanisms tailored for LLMs, including differential privacy, federated learning, cryptographic protocols, and trusted execution environments. We examine their efficacy in addressing key privacy challenges, such as membership inference and model inversion attacks, while balancing trade-offs between privacy and model utility. Furthermore, we analyze privacy-preserving applications of LLMs in privacy-sensitive domains, highlighting successful implementations and inherent limitations. Finally, this survey identifies emerging research directions, emphasizing the need for novel frameworks that integrate privacy by design into the lifecycle of LLMs. By synthesizing state-of-the-art approaches and future trends, this paper provides a foundation for developing robust, privacy-preserving large language models that safeguard sensitive information without compromising performance.

Please click each post's URL shown below to check out its full contents.

23.Agent - multiagent collaboration

  • Team: team-5
Multiagent

Summary of Post :

In this session, our readings cover:

Required Readings:

OmniParser v2: Advanced vision-based screen parsing for precisely grounded UI actions

Magentic-One: A generalist multi-agent system built on AutoGen

Multi-Agent Collaboration Mechanisms: A Survey of LLMs

Khanh-Tung Tran, Dung Dao, Minh-Duong Nguyen, Quoc-Viet Pham, Barry O’Sullivan, Hoang D. Nguyen With recent advances in Large Language Models (LLMs), Agentic AI has become phenomenal in real-world applications, moving toward multiple LLM-based agents to perceive, learn, reason, and act collaboratively. These LLM-based Multi-Agent Systems (MASs) enable groups of intelligent agents to coordinate and solve complex tasks collectively at scale, transitioning from isolated models to collaboration-centric approaches. This work provides an extensive survey of the collaborative aspect of MASs and introduces an extensible framework to guide future research. Our framework characterizes collaboration mechanisms based on key dimensions: actors (agents involved), types (e.g., cooperation, competition, or coopetition), structures (e.g., peer-to-peer, centralized, or distributed), strategies (e.g., role-based or model-based), and coordination protocols. Through a review of existing methodologies, our findings serve as a foundation for demystifying and advancing LLM-based MASs toward more intelligent and collaborative solutions for complex, real-world use cases. In addition, various applications of MASs across diverse domains, including 5G/6G networks, Industry 5.0, question answering, and social and cultural settings, are also investigated, demonstrating their wider adoption and broader impacts. Finally, we identify key lessons learned, open challenges, and potential research directions of MASs towards artificial collective intelligence.

A Review of Prominent Paradigms for LLM-Based Agents: Tool Use (Including RAG), Planning, and Feedback Learning

  • https://arxiv.org/abs/2406.05804
  • [Submitted on 9 Jun 2024 (v1), last revised 30 Nov 2024 (this version, v6)] Xinzhe Li
  • Tool use, planning, and feedback learning are currently three prominent paradigms for developing Large Language Model (LLM)-based agents across various tasks. Although numerous frameworks have been devised for each paradigm, their intricate workflows and inconsistent taxonomy create challenges in understanding and reviewing the frameworks across different paradigms. This survey introduces a unified taxonomy to systematically review and discuss these frameworks. Specifically, 1) the taxonomy defines environments/tasks, common LLM-profiled roles or LMPRs (policy models, evaluators, and dynamic models), and universally applicable workflows found in prior work, and 2) it enables a comparison of key perspectives on the implementations of LMPRs and workflow designs across different agent paradigms and frameworks. 3) Finally, we identify three limitations in existing workflow designs and systematically discuss the future work. Resources have been made publicly available at in our GitHub repository this https URL.
  • Comments: CoLing 2025 Camera Ready (extended to 9 pages)

Agent-as-a-Judge: Evaluate Agents with Agents

  • [Submitted on 14 Oct 2024 (v1), last revised 16 Oct 2024 (this version, v2)]
  • Mingchen Zhuge, Changsheng Zhao, Dylan Ashley, Wenyi Wang, Dmitrii Khizbullin, Yunyang Xiong, Zechun Liu, Ernie Chang, Raghuraman Krishnamoorthi, Yuandong Tian, Yangyang Shi, Vikas Chandra, Jürgen Schmidhuber
  • Contemporary evaluation techniques are inadequate for agentic systems. These approaches either focus exclusively on final outcomes – ignoring the step-by-step nature of agentic systems, or require excessive manual labour. To address this, we introduce the Agent-as-a-Judge framework, wherein agentic systems are used to evaluate agentic systems. This is an organic extension of the LLM-as-a-Judge framework, incorporating agentic features that enable intermediate feedback for the entire task-solving process. We apply the Agent-as-a-Judge to the task of code generation. To overcome issues with existing benchmarks and provide a proof-of-concept testbed for Agent-as-a-Judge, we present DevAI, a new benchmark of 55 realistic automated AI development tasks. It includes rich manual annotations, like a total of 365 hierarchical user requirements. We benchmark three of the popular agentic systems using Agent-as-a-Judge and find it dramatically outperforms LLM-as-a-Judge and is as reliable as our human evaluation baseline. Altogether, we believe that Agent-as-a-Judge marks a concrete step forward for modern agentic systems – by providing rich and reliable reward signals necessary for dynamic and scalable self-improvement. Comments: The project can be found at this https URL. The dataset is released at this https URL

A Survey on Large Language Model based Autonomous Agents

  • [Submitted on 22 Aug 2023 (v1), last revised 15 Dec 2024 (this version, v6)]
  • URL
  • Lei Wang, Chen Ma, Xueyang Feng, Zeyu Zhang, Hao Yang, Jingsen Zhang, Zhiyuan Chen, Jiakai Tang, Xu Chen, Yankai Lin, Wayne Xin Zhao, Zhewei Wei, Ji-Rong Wen
  • Autonomous agents have long been a prominent research focus in both academic and industry communities. Previous research in this field often focuses on training agents with limited knowledge within isolated environments, which diverges significantly from human learning processes, and thus makes the agents hard to achieve human-like decisions. Recently, through the acquisition of vast amounts of web knowledge, large language models (LLMs) have demonstrated remarkable potential in achieving human-level intelligence. This has sparked an upsurge in studies investigating LLM-based autonomous agents. In this paper, we present a comprehensive survey of these studies, delivering a systematic review of the field of LLM-based autonomous agents from a holistic perspective. More specifically, we first discuss the construction of LLM-based autonomous agents, for which we propose a unified framework that encompasses a majority of the previous work. Then, we present a comprehensive overview of the diverse applications of LLM-based autonomous agents in the fields of social science, natural science, and engineering. Finally, we delve into the evaluation strategies commonly used for LLM-based autonomous agents. Based on the previous studies, we also present several challenges and future directions in this field. To keep track of this field and continuously update our survey, we maintain a repository of relevant references at this https URL. Comments: change several 35 pages, 5 figures, 3 tables

Deploying Foundation Model Powered Agent Services: A Survey

  • Wenchao Xu, Jinyu Chen, Peirong Zheng, Xiaoquan Yi, Tianyi Tian, Wenhui Zhu, Quan Wan, Haozhao Wang, Yunfeng Fan, Qinliang Su, Xuemin Shen
  • [Submitted on 18 Dec 2024]
  • Foundation model (FM) powered agent services are regarded as a promising solution to develop intelligent and personalized applications for advancing toward Artificial General Intelligence (AGI). To achieve high reliability and scalability in deploying these agent services, it is essential to collaboratively optimize computational and communication resources, thereby ensuring effective resource allocation and seamless service delivery. In pursuit of this vision, this paper proposes a unified framework aimed at providing a comprehensive survey on deploying FM-based agent services across heterogeneous devices, with the emphasis on the integration of model and resource optimization to establish a robust infrastructure for these services. Particularly, this paper begins with exploring various low-level optimization strategies during inference and studies approaches that enhance system scalability, such as parallelism techniques and resource scaling methods. The paper then discusses several prominent FMs and investigates research efforts focused on inference acceleration, including techniques such as model compression and token reduction. Moreover, the paper also investigates critical components for constructing agent services and highlights notable intelligent applications. Finally, the paper presents potential research directions for developing real-time agent services with high Quality of Service (QoS).

GUI Agents: A Survey

  • [Submitted on 18 Dec 2024]
  • Dang Nguyen, Jian Chen, Yu Wang, Gang Wu, Namyong Park, Zhengmian Hu, Hanjia Lyu, Junda Wu, Ryan Aponte, Yu Xia, Xintong Li, Jing Shi, Hongjie Chen, Viet Dac Lai, Zhouhang Xie, Sungchul Kim, Ruiyi Zhang, Tong Yu, Mehrab Tanjim, Nesreen K. Ahmed, Puneet Mathur, Seunghyun Yoon, Lina Yao, Branislav Kveton, Thien Huu Nguyen, Trung Bui, Tianyi Zhou, Ryan A. Rossi, Franck Dernoncourt
  • Graphical User Interface (GUI) agents, powered by Large Foundation Models, have emerged as a transformative approach to automating human-computer interaction. These agents autonomously interact with digital systems or software applications via GUIs, emulating human actions such as clicking, typing, and navigating visual elements across diverse platforms. Motivated by the growing interest and fundamental importance of GUI agents, we provide a comprehensive survey that categorizes their benchmarks, evaluation metrics, architectures, and training methods. We propose a unified framework that delineates their perception, reasoning, planning, and acting capabilities. Furthermore, we identify important open challenges and discuss key future directions. Finally, this work serves as a basis for practitioners and researchers to gain an intuitive understanding of current progress, techniques, benchmarks, and critical open problems that remain to be addressed.

More Readings:

Agent Laboratory: Using LLM Agents as Research Assistants

  • [Submitted on 8 Jan 2025]
  • Samuel Schmidgall, Yusheng Su, Ze Wang, Ximeng Sun, Jialian Wu, Xiaodong Yu, Jiang Liu, Zicheng Liu, Emad Barsoum
  • Historically, scientific discovery has been a lengthy and costly process, demanding substantial time and resources from initial conception to final results. To accelerate scientific discovery, reduce research costs, and improve research quality, we introduce Agent Laboratory, an autonomous LLM-based framework capable of completing the entire research process. This framework accepts a human-provided research idea and progresses through three stages–literature review, experimentation, and report writing to produce comprehensive research outputs, including a code repository and a research report, while enabling users to provide feedback and guidance at each stage. We deploy Agent Laboratory with various state-of-the-art LLMs and invite multiple researchers to assess its quality by participating in a survey, providing human feedback to guide the research process, and then evaluate the final paper. We found that: (1) Agent Laboratory driven by o1-preview generates the best research outcomes; (2) The generated machine learning code is able to achieve state-of-the-art performance compared to existing methods; (3) Human involvement, providing feedback at each stage, significantly improves the overall quality of research; (4) Agent Laboratory significantly reduces research expenses, achieving an 84% decrease compared to previous autonomous research methods. We hope Agent Laboratory enables researchers to allocate more effort toward creative ideation rather than low-level coding and writing, ultimately accelerating scientific discovery.

Please click each post's URL shown below to check out its full contents.

24.Agent Efficiency - Model Serving + PPO

Customization Serving

Summary of Post :

In this session, our readings cover:

Required Readings:

FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness

  • Tri Dao, Daniel Y. Fu, Stefano Ermon, Atri Rudra, Christopher Ré
  • [Submitted on 27 May 2022 (v1), last revised 23 Jun 2022 (this version, v2)]
  • Transformers are slow and memory-hungry on long sequences, since the time and memory complexity of self-attention are quadratic in sequence length. Approximate attention methods have attempted to address this problem by trading off model quality to reduce the compute complexity, but often do not achieve wall-clock speedup. We argue that a missing principle is making attention algorithms IO-aware – accounting for reads and writes between levels of GPU memory. We propose FlashAttention, an IO-aware exact attention algorithm that uses tiling to reduce the number of memory reads/writes between GPU high bandwidth memory (HBM) and GPU on-chip SRAM. We analyze the IO complexity of FlashAttention, showing that it requires fewer HBM accesses than standard attention, and is optimal for a range of SRAM sizes. We also extend FlashAttention to block-sparse attention, yielding an approximate attention algorithm that is faster than any existing approximate attention method. FlashAttention trains Transformers faster than existing baselines: 15% end-to-end wall-clock speedup on BERT-large (seq. length 512) compared to the MLPerf 1.1 training speed record, 3× speedup on GPT-2 (seq. length 1K), and 2.4× speedup on long-range arena (seq. length 1K-4K). FlashAttention and block-sparse FlashAttention enable longer context in Transformers, yielding higher quality models (0.7 better perplexity on GPT-2 and 6.4 points of lift on long-document classification) and entirely new capabilities: the first Transformers to achieve better-than-chance performance on the Path-X challenge (seq. length 16K, 61.4% accuracy) and Path-256 (seq. length 64K, 63.1% accuracy).

FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning

  • Tri Dao
  • [Submitted on 17 Jul 2023]
  • Scaling Transformers to longer sequence lengths has been a major problem in the last several years, promising to improve performance in language modeling and high-resolution image understanding, as well as to unlock new applications in code, audio, and video generation. The attention layer is the main bottleneck in scaling to longer sequences, as its runtime and memory increase quadratically in the sequence length. FlashAttention exploits the asymmetric GPU memory hierarchy to bring significant memory saving (linear instead of quadratic) and runtime speedup (2-4× compared to optimized baselines), with no approximation. However, FlashAttention is still not nearly as fast as optimized matrix-multiply (GEMM) operations, reaching only 25-40\% of the theoretical maximum FLOPs/s. We observe that the inefficiency is due to suboptimal work partitioning between different thread blocks and warps on the GPU, causing either low-occupancy or unnecessary shared memory reads/writes. We propose FlashAttention-2, with better work partitioning to address these issues. In particular, we (1) tweak the algorithm to reduce the number of non-matmul FLOPs (2) parallelize the attention computation, even for a single head, across different thread blocks to increase occupancy, and (3) within each thread block, distribute the work between warps to reduce communication through shared memory. These yield around 2× speedup compared to FlashAttention, reaching 50-73\% of the theoretical maximum FLOPs/s on A100 and getting close to the efficiency of GEMM operations. We empirically validate that when used end-to-end to train GPT-style models, FlashAttention-2 reaches training speed of up to 225 TFLOPs/s per A100 GPU (72\% model FLOPs utilization).

Efficient Transformers: A Survey

  • Yi Tay, Mostafa Dehghani, Dara Bahri, Donald Metzler
  • [Submitted on 14 Sep 2020 (v1), last revised 14 Mar 2022 (this version, v3)]
  • Transformer model architectures have garnered immense interest lately due to their effectiveness across a range of domains like language, vision and reinforcement learning. In the field of natural language processing for example, Transformers have become an indispensable staple in the modern deep learning stack. Recently, a dizzying number of “X-former” models have been proposed - Reformer, Linformer, Performer, Longformer, to name a few - which improve upon the original Transformer architecture, many of which make improvements around computational and memory efficiency. With the aim of helping the avid researcher navigate this flurry, this paper characterizes a large and thoughtful selection of recent efficiency-flavored “X-former” models, providing an organized and comprehensive overview of existing work and models across multiple domains.

PPO Readings:

Towards a Unified View of Preference Learning for Large Language Models: A Survey

  • [Submitted on 4 Sep 2024 (v1), last revised 31 Oct 2024 (this version, v5)]
  • Bofei Gao, Feifan Song, Yibo Miao, Zefan Cai, Zhe Yang, Liang Chen, Helan Hu, Runxin Xu, Qingxiu Dong, Ce Zheng, Shanghaoran Quan, Wen Xiao, Ge Zhang, Daoguang Zan, Keming Lu, Bowen Yu, Dayiheng Liu, Zeyu Cui, Jian Yang, Lei Sha, Houfeng Wang, Zhifang Sui, Peiyi Wang, Tianyu Liu, Baobao Chang
  • Large Language Models (LLMs) exhibit remarkably powerful capabilities. One of the crucial factors to achieve success is aligning the LLM’s output with human preferences. This alignment process often requires only a small amount of data to efficiently enhance the LLM’s performance. While effective, research in this area spans multiple domains, and the methods involved are relatively complex to understand. The relationships between different methods have been under-explored, limiting the development of the preference alignment. In light of this, we break down the existing popular alignment strategies into different components and provide a unified framework to study the current alignment strategies, thereby establishing connections among them. In this survey, we decompose all the strategies in preference learning into four components: model, data, feedback, and algorithm. This unified view offers an in-depth understanding of existing alignment algorithms and also opens up possibilities to synergize the strengths of different strategies. Furthermore, we present detailed working examples of prevalent existing algorithms to facilitate a comprehensive understanding for the readers. Finally, based on our unified perspective, we explore the challenges and future research directions for aligning large language models with human preferences.

Insights into Alignment: Evaluating DPO and its Variants Across Multiple Tasks

  • Amir Saeidi, Shivanshu Verma, Md Nayem Uddin, Chitta Baral
  • This study evaluates Direct Preference Optimization (DPO) and its variants for aligning Large Language Models (LLMs) with human preferences, testing three configurations: (1) with Supervised Fine Tuning (SFT), (2) without SFT, and (3) without SFT but using an instruction tuned model. We further investigate how training set size influences model performance. Our evaluation spans 13 benchmarks covering dialogue, reasoning, mathematical problem-solving, question answering, truthfulness, MT-Bench, Big Bench, and the Open LLM Leaderboard. We find that: (1) alignment methods often achieve near optimal performance even with smaller subsets of training data; (2) although they offer limited improvements on complex reasoning tasks, they enhance mathematical problem-solving; and (3) using an instruction tuned model improves truthfulness. These insights highlight the conditions under which alignment methods excel, as well as their limitations.

More Readings:

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

  • [Submitted on 22 Jan 2025]
  • DeepSeek-AI, (100 additional authors not shown)
  • We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step, demonstrates remarkable reasoning capabilities. Through RL, DeepSeek-R1-Zero naturally emerges with numerous powerful and intriguing reasoning behaviors. However, it encounters challenges such as poor readability, and language mixing. To address these issues and further enhance reasoning performance, we introduce DeepSeek-R1, which incorporates multi-stage training and cold-start data before RL. DeepSeek-R1 achieves performance comparable to OpenAI-o1-1217 on reasoning tasks. To support the research community, we open-source DeepSeek-R1-Zero, DeepSeek-R1, and six dense models (1.5B, 7B, 8B, 14B, 32B, 70B) distilled from DeepSeek-R1 based on Qwen and Llama.

Please click each post's URL shown below to check out its full contents.

25.Project discussion session!

  • Team: QA discussion date
  • Team: instructor

Summary of Post :

In this session, our readings cover:

Required Readings:

  • https://www.phontron.com/slides/neubig24softwareagents.pdf

More Readings:


Please click each post's URL shown below to check out its full contents.

26.multimodal FMs - video / audio

  • Team: team-2
Multimodal

Summary of Post :

In this session, our readings cover:

Required Readings:

NVLM: Open Frontier-Class Multimodal LLMs

  • [Submitted on 17 Sep 2024 (v1), last revised 22 Oct 2024 (this version, v2)]
  • Wenliang Dai, Nayeon Lee, Boxin Wang, Zhuolin Yang, Zihan Liu, Jon Barker, Tuomas Rintamaki, Mohammad Shoeybi, Bryan Catanzaro, Wei Ping
  • We introduce NVLM 1.0, a family of frontier-class multimodal large language models (LLMs) that achieve state-of-the-art results on vision-language tasks, rivaling the leading proprietary models (e.g., GPT-4o) and open-access models (e.g., Llama 3-V 405B and InternVL 2). Remarkably, NVLM 1.0 shows improved text-only performance over its LLM backbone after multimodal training. In terms of model design, we perform a comprehensive comparison between decoder-only multimodal LLMs (e.g., LLaVA) and cross-attention-based models (e.g., Flamingo). Based on the strengths and weaknesses of both approaches, we propose a novel architecture that enhances both training efficiency and multimodal reasoning capabilities. Furthermore, we introduce a 1-D tile-tagging design for tile-based dynamic high-resolution images, which significantly boosts performance on multimodal reasoning and OCR-related tasks. Regarding training data, we meticulously curate and provide detailed information on our multimodal pretraining and supervised fine-tuning datasets. Our findings indicate that dataset quality and task diversity are more important than scale, even during the pretraining phase, across all architectures. Notably, we develop production-grade multimodality for the NVLM-1.0 models, enabling them to excel in vision-language tasks while maintaining and even improving text-only performance compared to their LLM backbones. To achieve this, we craft and integrate a high-quality text-only dataset into multimodal training, alongside a substantial amount of multimodal math and reasoning data, leading to enhanced math and coding capabilities across modalities. To advance research in the field, we release the model weights at this https URL and will open-source the training code for the community soon.

  • There are two main approaches to building multimodal LLMs: - Method A: Unified Embedding Decoder Architecture approach;
    • Method B: Cross-modality Attention Architecture approach.
  • Directly compared:
    • Method A: The Unified Embedding Decoder Architecture (“decoder-only architecture,” NVLM-D),
    • Method B: The Cross-Modality Attention Architecture (“cross-attention-based architecture,” NVLM-X),
    • A hybrid approach (NVLM-H).
  • Key findings are as follows:
    • NVLM-X: Offers superior computational efficiency for high-resolution images.
    • NVLM-D: Delivers higher accuracy for OCR-related tasks.
    • NVLM-H: Combines the strengths of both approaches for optimal performance.

LLMs Meet Multimodal Generation and Editing: A Survey

  • [Submitted on 29 May 2024 (v1), last revised 9 Jun 2024 (this version, v2)]
  • Yingqing He, Zhaoyang Liu, Jingye Chen, Zeyue Tian, Hongyu Liu, Xiaowei Chi, Runtao Liu, Ruibin Yuan, Yazhou Xing, Wenhai Wang, Jifeng Dai, Yong Zhang, Wei Xue, Qifeng Liu, Yike Guo, Qifeng Chen
  • With the recent advancement in large language models (LLMs), there is a growing interest in combining LLMs with multimodal learning. Previous surveys of multimodal large language models (MLLMs) mainly focus on multimodal understanding. This survey elaborates on multimodal generation and editing across various domains, comprising image, video, 3D, and audio. Specifically, we summarize the notable advancements with milestone works in these fields and categorize these studies into LLM-based and CLIP/T5-based methods. Then, we summarize the various roles of LLMs in multimodal generation and exhaustively investigate the critical technical components behind these methods and the multimodal datasets utilized in these studies. Additionally, we dig into tool-augmented multimodal agents that can leverage existing generative models for human-computer interaction. Lastly, we discuss the advancements in the generative AI safety field, investigate emerging applications, and discuss future prospects. Our work provides a systematic and insightful overview of multimodal generation and processing, which is expected to advance the development of Artificial Intelligence for Generative Content (AIGC) and world models. A curated list of all related papers can be found at this https URL

A Survey on Speech Large Language Models

  • Jing Peng, Yucheng Wang, Yu Xi, Xu Li, Xizhuo Zhang, Kai Yu
  • [Submitted on 24 Oct 2024 (v1), last revised 25 Oct 2024 (this version, v2)]
  • Large Language Models (LLMs) exhibit strong contextual understanding and remarkable multi-task performance. Therefore, researchers have been seeking to integrate LLMs in the broad sense of Spoken Language Understanding (SLU) field. Different from the traditional method of cascading LLMs to process text generated by Automatic Speech Recognition(ASR), new efforts have focused on designing architectures centered around Audio Feature Extraction - Multimodal Information Fusion - LLM Inference(Speech LLMs). This approach enables richer audio feature extraction while simultaneously facilitating end-to-end fusion of audio and text modalities, thereby achieving deeper understanding and reasoning from audio data. This paper elucidates the development of Speech LLMs, offering an in-depth analysis of system architectures and training strategies. Through extensive research and a series of targeted experiments, the paper assesses Speech LLMs’ advancements in Rich Audio Transcription and its potential for Cross-task Integration within the SLU field. Additionally, it indicates key challenges uncovered through experimentation, such as the Dormancy of LLMs under certain conditions. The paper further delves into the training strategies for Speech LLMs, proposing potential solutions based on these findings, and offering valuable insights and references for future research in this domain, as well as LLM applications in multimodal contexts.

Video Understanding with Large Language Models: A Survey

  • Yunlong Tang, Jing Bi, Siting Xu, Luchuan Song, Susan Liang, Teng Wang, Daoan Zhang, Jie An, Jingyang Lin, Rongyi Zhu, Ali Vosoughi, Chao Huang, Zeliang Zhang, Pinxin Liu, Mingqian Feng, Feng Zheng, Jianguo Zhang, Ping Luo, Jiebo Luo, Chenliang Xu
  • [Submitted on 29 Dec 2023 (v1), last revised 24 Jul 2024 (this version, v4)]
  • With the burgeoning growth of online video platforms and the escalating volume of video content, the demand for proficient video understanding tools has intensified markedly. Given the remarkable capabilities of large language models (LLMs) in language and multimodal tasks, this survey provides a detailed overview of recent advancements in video understanding that harness the power of LLMs (Vid-LLMs). The emergent capabilities of Vid-LLMs are surprisingly advanced, particularly their ability for open-ended multi-granularity (general, temporal, and spatiotemporal) reasoning combined with commonsense knowledge, suggesting a promising path for future video understanding. We examine the unique characteristics and capabilities of Vid-LLMs, categorizing the approaches into three main types: Video Analyzer x LLM, Video Embedder x LLM, and (Analyzer + Embedder) x LLM. Furthermore, we identify five sub-types based on the functions of LLMs in Vid-LLMs: LLM as Summarizer, LLM as Manager, LLM as Text Decoder, LLM as Regressor, and LLM as Hidden Layer. Furthermore, this survey presents a comprehensive study of the tasks, datasets, benchmarks, and evaluation methodologies for Vid-LLMs. Additionally, it explores the expansive applications of Vid-LLMs across various domains, highlighting their remarkable scalability and versatility in real-world video understanding challenges. Finally, it summarizes the limitations of existing Vid-LLMs and outlines directions for future research. For more information, readers are recommended to visit the repository at this https URL.

Beta Release of Zonos-v0.1

FEBRUARY 10, 2025 PALO ALTO, CALIFORNIA We are excited to announce the release of Zonos-v0.1 beta, featuring two expressive and real-time text-to-speech (TTS) models with high-fidelity voice cloning. We are releasing our 1.6B transformer and 1.6B hybrid under an Apache 2.0 license.


Please click each post's URL shown below to check out its full contents.

27.Small foundation models

  • Team: team-3
Scaling

Summary of Post :

In this session, our readings cover:

Required Readings:

rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking

  • [Submitted on 8 Jan 2025]
  • Xinyu Guan, Li Lyna Zhang, Yifei Liu, Ning Shang, Youran Sun, Yi Zhu, Fan Yang, Mao Yang
  • We present rStar-Math to demonstrate that small language models (SLMs) can rival or even surpass the math reasoning capability of OpenAI o1, without distillation from superior models. rStar-Math achieves this by exercising “deep thinking” through Monte Carlo Tree Search (MCTS), where a math policy SLM performs test-time search guided by an SLM-based process reward model. rStar-Math introduces three innovations to tackle the challenges in training the two SLMs: (1) a novel code-augmented CoT data sythesis method, which performs extensive MCTS rollouts to generate step-by-step verified reasoning trajectories used to train the policy SLM; (2) a novel process reward model training method that avoids naïve step-level score annotation, yielding a more effective process preference model (PPM); (3) a self-evolution recipe in which the policy SLM and PPM are built from scratch and iteratively evolved to improve reasoning capabilities. Through 4 rounds of self-evolution with millions of synthesized solutions for 747k math problems, rStar-Math boosts SLMs’ math reasoning to state-of-the-art levels. On the MATH benchmark, it improves Qwen2.5-Math-7B from 58.8% to 90.0% and Phi3-mini-3.8B from 41.4% to 86.4%, surpassing o1-preview by +4.5% and +0.9%. On the USA Math Olympiad (AIME), rStar-Math solves an average of 53.3% (8/15) of problems, ranking among the top 20% the brightest high school math students. Code and data will be available at this https URL.

Phi-4 Technical Report

  • https://arxiv.org/abs/2412.08905
  • Marah Abdin, Jyoti Aneja, Harkirat Behl, Sébastien Bubeck, Ronen Eldan, Suriya Gunasekar, Michael Harrison, Russell J. Hewett, Mojan Javaheripi, Piero Kauffmann, James R. Lee, Yin Tat Lee, Yuanzhi Li, Weishung Liu, Caio C. T. Mendes, Anh Nguyen, Eric Price, Gustavo de Rosa, Olli Saarikivi, Adil Salim, Shital Shah, Xin Wang, Rachel Ward, Yue Wu, Dingli Yu, Cyril Zhang, Yi Zhang
  • We present phi-4, a 14-billion parameter language model developed with a training recipe that is centrally focused on data quality. Unlike most language models, where pre-training is based primarily on organic data sources such as web content or code, phi-4 strategically incorporates synthetic data throughout the training process. While previous models in the Phi family largely distill the capabilities of a teacher model (specifically GPT-4), phi-4 substantially surpasses its teacher model on STEM-focused QA capabilities, giving evidence that our data-generation and post-training techniques go beyond distillation. Despite minimal changes to the phi-3 architecture, phi-4 achieves strong performance relative to its size – especially on reasoning-focused benchmarks – due to improved data, training curriculum, and innovations in the post-training scheme.

Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling

  • [Submitted on 29 Aug 2024 (v1), last revised 7 Oct 2024 (this version, v2)]
  • https://arxiv.org/abs/2408.16737
  • Hritik Bansal, Arian Hosseini, Rishabh Agarwal, Vinh Q. Tran, Mehran Kazemi
  • Training on high-quality synthetic data from strong language models (LMs) is a common strategy to improve the reasoning performance of LMs. In this work, we revisit whether this strategy is compute-optimal under a fixed inference budget (e.g., FLOPs). To do so, we investigate the trade-offs between generating synthetic data using a stronger but more expensive (SE) model versus a weaker but cheaper (WC) model. We evaluate the generated data across three key metrics: coverage, diversity, and false positive rate, and show that the data from WC models may have higher coverage and diversity, but also exhibit higher false positive rates. We then finetune LMs on data from SE and WC models in different settings: knowledge distillation, self-improvement, and a novel weak-to-strong improvement setup where a weaker LM teaches reasoning to a stronger LM. Our findings reveal that models finetuned on WC-generated data consistently outperform those trained on SE-generated data across multiple benchmarks and multiple choices of WC and SE models. These results challenge the prevailing practice of relying on SE models for synthetic data generation, suggesting that WC may be the compute-optimal approach for training advanced LM reasoners.

More Readings:

Synthetica: Large Scale Synthetic Data for Robot Perception

  • [Submitted on 28 Oct 2024]
  • Ritvik Singh, Jingzhou Liu, Karl Van Wyk, Yu-Wei Chao, Jean-Francois Lafleche, Florian Shkurti, Nathan Ratliff, Ankur Handa
  • Vision-based object detectors are a crucial basis for robotics applications as they provide valuable information about object localisation in the environment. These need to ensure high reliability in different lighting conditions, occlusions, and visual artifacts, all while running in real-time. Collecting and annotating real-world data for these networks is prohibitively time consuming and costly, especially for custom assets, such as industrial objects, making it untenable for generalization to in-the-wild scenarios. To this end, we present Synthetica, a method for large-scale synthetic data generation for training robust state estimators. This paper focuses on the task of object detection, an important problem which can serve as the front-end for most state estimation problems, such as pose estimation. Leveraging data from a photorealistic ray-tracing renderer, we scale up data generation, generating 2.7 million images, to train highly accurate real-time detection transformers. We present a collection of rendering randomization and training-time data augmentation techniques conducive to robust sim-to-real performance for vision tasks. We demonstrate state-of-the-art performance on the task of object detection while having detectors that run at 50-100Hz which is 9 times faster than the prior SOTA. We further demonstrate the usefulness of our training methodology for robotics applications by showcasing a pipeline for use in the real world with custom objects for which there do not exist prior datasets. Our work highlights the importance of scaling synthetic data generation for robust sim-to-real transfer while achieving the fastest real-time inference speeds. Videos and supplementary information can be found at this URL: this https URL.

Small Language Models (SLMs) Can Still Pack a Punch: A survey

  • [Submitted on 3 Jan 2025]
  • Shreyas Subramanian, Vikram Elango, Mecit Gungor
  • As foundation AI models continue to increase in size, an important question arises - is massive scale the only path forward? This survey of about 160 papers presents a family of Small Language Models (SLMs) in the 1 to 8 billion parameter range that demonstrate smaller models can perform as well, or even outperform large models. We explore task agnostic, general purpose SLMs, task-specific SLMs and techniques to create SLMs that can guide the community to build models while balancing performance, efficiency, scalability and cost. Furthermore we define and characterize SLMs’ effective sizes, representing increased capability with respect to LLMs.

Please click each post's URL shown below to check out its full contents.

28.Model Interpretibility for FM

  • Team: team-4

Summary of Post :

In this session, our readings cover:

Required Readings:

Mapping the Mind of a Large Language Model

Using Dictionary Learning Features as Classifiers

Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities

Zora Che, Stephen Casper, Robert Kirk, Anirudh Satheesh, Stewart Slocum, Lev E McKinney, Rohit Gandikota, Aidan Ewart, Domenic Rosati, Zichu Wu, Zikui Cai, Bilal Chughtai, Yarin Gal, Furong Huang, Dylan Hadfield-Menell Evaluations of large language model (LLM) risks and capabilities are increasingly being incorporated into AI risk management and governance frameworks. Currently, most risk evaluations are conducted by designing inputs that elicit harmful behaviors from the system. However, a fundamental limitation of this approach is that the harmfulness of the behaviors identified during any particular evaluation can only lower bound the model’s worst-possible-case behavior. As a complementary method for eliciting harmful behaviors, we propose evaluating LLMs with model tampering attacks which allow for modifications to latent activations or weights. We pit state-of-the-art techniques for removing harmful LLM capabilities against a suite of 5 input-space and 6 model tampering attacks. In addition to benchmarking these methods against each other, we show that (1) model resilience to capability elicitation attacks lies on a low-dimensional robustness subspace; (2) the attack success rate of model tampering attacks can empirically predict and offer conservative estimates for the success of held-out input-space attacks; and (3) state-of-the-art unlearning methods can easily be undone within 16 steps of fine-tuning. Together these results highlight the difficulty of removing harmful LLM capabilities and show that model tampering attacks enable substantially more rigorous evaluations than input-space attacks alone. We release models at this https URL

Agent-as-a-Judge: Evaluate Agents with Agents

  • [Submitted on 14 Oct 2024 (v1), last revised 16 Oct 2024 (this version, v2)]
  • Mingchen Zhuge, Changsheng Zhao, Dylan Ashley, Wenyi Wang, Dmitrii Khizbullin, Yunyang Xiong, Zechun Liu, Ernie Chang, Raghuraman Krishnamoorthi, Yuandong Tian, Yangyang Shi, Vikas Chandra, Jürgen Schmidhuber
  • Contemporary evaluation techniques are inadequate for agentic systems. These approaches either focus exclusively on final outcomes – ignoring the step-by-step nature of agentic systems, or require excessive manual labour. To address this, we introduce the Agent-as-a-Judge framework, wherein agentic systems are used to evaluate agentic systems. This is an organic extension of the LLM-as-a-Judge framework, incorporating agentic features that enable intermediate feedback for the entire task-solving process. We apply the Agent-as-a-Judge to the task of code generation. To overcome issues with existing benchmarks and provide a proof-of-concept testbed for Agent-as-a-Judge, we present DevAI, a new benchmark of 55 realistic automated AI development tasks. It includes rich manual annotations, like a total of 365 hierarchical user requirements. We benchmark three of the popular agentic systems using Agent-as-a-Judge and find it dramatically outperforms LLM-as-a-Judge and is as reliable as our human evaluation baseline. Altogether, we believe that Agent-as-a-Judge marks a concrete step forward for modern agentic systems – by providing rich and reliable reward signals necessary for dynamic and scalable self-improvement. Comments: The project can be found at this https URL. The dataset is released at this https URL

More Readings:

A Survey on Large Language Models with some Insights on their Capabilities and Limitations

  • [Submitted on 3 Jan 2025]
  • Andrea Matarazzo, Riccardo Torlone
  • The rapid advancement of artificial intelligence, particularly with the development of Large Language Models (LLMs) built on the transformer architecture, has redefined the capabilities of natural language processing. These models now exhibit remarkable performance across various language-related tasks, such as text generation, question answering, translation, and summarization, often rivaling human-like comprehension. More intriguingly, LLMs have demonstrated emergent abilities extending beyond their core functions, showing proficiency in tasks like commonsense reasoning, code generation, and arithmetic. This survey paper explores the foundational components, scaling mechanisms, and architectural strategies that drive these capabilities. Emphasizing models like GPT and LLaMA, we analyze the impact of exponential data and computational growth on LLM performance, while also addressing the trade-offs associated with scaling. We also examine LLM applications across sectors, such as healthcare, finance, education, and law, highlighting their adaptability and potential to solve domain-specific challenges. Central to this work are the questions of how LLMs generalize across diverse tasks, exhibit planning, and reasoning abilities, and whether these emergent abilities can be systematically elicited or enhanced. In particular, we provide some insights into the CoT (Chain of Thought) and PoT (Plan of Thought) abilities within LLMs, focusing on how pre-training data influences their emergence. Additionally, we investigate LLM-modulo frameworks that integrate external systems, allowing LLMs to handle complex, dynamic tasks. By analyzing these factors, this paper aims to foster the ongoing discussion on the capabilities and limits of LLMs, promoting their responsible development and application in novel and increasingly complex environments.

Please click each post's URL shown below to check out its full contents.

29.Inference test time scaling law

  • Team: team-5
Scaling

Summary of Post :

In this session, our readings cover:

Required Readings:

Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

  • [Submitted on 6 Aug 2024]
  • URL
  • Charlie Snell, Jaehoon Lee, Kelvin Xu, Aviral Kumar
  • Enabling LLMs to improve their outputs by using more test-time computation is a critical step towards building generally self-improving agents that can operate on open-ended natural language. In this paper, we study the scaling of inference-time computation in LLMs, with a focus on answering the question: if an LLM is allowed to use a fixed but non-trivial amount of inference-time compute, how much can it improve its performance on a challenging prompt? Answering this question has implications not only on the achievable performance of LLMs, but also on the future of LLM pretraining and how one should tradeoff inference-time and pre-training compute. Despite its importance, little research attempted to understand the scaling behaviors of various test-time inference methods. Moreover, current work largely provides negative results for a number of these strategies. In this work, we analyze two primary mechanisms to scale test-time computation: (1) searching against dense, process-based verifier reward models; and (2) updating the model’s distribution over a response adaptively, given the prompt at test time. We find that in both cases, the effectiveness of different approaches to scaling test-time compute critically varies depending on the difficulty of the prompt. This observation motivates applying a “compute-optimal” scaling strategy, which acts to most effectively allocate test-time compute adaptively per prompt. Using this compute-optimal strategy, we can improve the efficiency of test-time compute scaling by more than 4x compared to a best-of-N baseline. Additionally, in a FLOPs-matched evaluation, we find that on problems where a smaller base model attains somewhat non-trivial success rates, test-time compute can be used to outperform a 14x larger model.

Tulu 3: Pushing Frontiers in Open Language Model Post-Training

  • URL
  • [Submitted on 22 Nov 2024 (v1), last revised 29 Jan 2025 (this version, v3)]
  • Nathan Lambert, Jacob Morrison, Valentina Pyatkin, Shengyi Huang, Hamish Ivison, Faeze Brahman, Lester James V. Miranda, Alisa Liu, Nouha Dziri, Shane Lyu, Yuling Gu, Saumya Malik, Victoria Graf, Jena D. Hwang, Jiangjiang Yang, Ronan Le Bras, Oyvind Tafjord, Chris Wilhelm, Luca Soldaini, Noah A. Smith, Yizhong Wang, Pradeep Dasigi, Hannaneh Hajishirzi
  • Language model post-training is applied to refine behaviors and unlock new skills across a wide range of recent language models, but open recipes for applying these techniques lag behind proprietary ones. The underlying training data and recipes for post-training are simultaneously the most important pieces of the puzzle and the portion with the least transparency. To bridge this gap, we introduce Tulu 3, a family of fully-open state-of-the-art post-trained models, alongside its data, code, and training recipes, serving as a comprehensive guide for modern post-training techniques. Tulu 3, which builds on Llama 3.1 base models, achieves results surpassing the instruct versions of Llama 3.1, Qwen 2.5, Mistral, and even closed models such as GPT-4o-mini and Claude 3.5-Haiku. The training algorithms for our models include supervised finetuning (SFT), Direct Preference Optimization (DPO), and a novel method we call Reinforcement Learning with Verifiable Rewards (RLVR). With Tulu 3, we introduce a multi-task evaluation scheme for post-training recipes with development and unseen evaluations, standard benchmark implementations, and substantial decontamination of existing open datasets on said benchmarks. We conclude with analysis and discussion of training methods that did not reliably improve performance. In addition to the Tulu 3 model weights and demo, we release the complete recipe – including datasets for diverse core skills, a robust toolkit for data curation and evaluation, the training code and infrastructure, and, most importantly, a detailed report for reproducing and further adapting the Tulu 3 approach to more domains.

Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models

  • [Submitted on 1 Aug 2024 (v1), last revised 14 Oct 2024 (this version, v2)]
  • Yangzhen Wu, Zhiqing Sun, Shanda Li, Sean Welleck, Yiming Yang
  • While the scaling laws of large language models (LLMs) training have been extensively studied, optimal inference configurations of LLMs remain underexplored. We study inference scaling laws and compute-optimal inference, focusing on the trade-offs between model sizes and generating additional tokens with different inference strategies. As a first step towards understanding and designing compute-optimal inference methods, we studied cost-performance trade-offs for inference strategies such as greedy search, majority voting, best-of-n, weighted voting, and two different tree search algorithms, using different model sizes and compute budgets. Our findings indicate smaller models (e.g., Llemma-7B) can outperform larger models given the same computation budgets, and that smaller models paired with advanced inference algorithms yield Pareto-optimal cost-performance trade-offs. For instance, the Llemma-7B model, equipped with our novel tree search algorithm, consistently outperforms Llemma-34B with standard majority voting on the MATH benchmark across all FLOPs budgets. We hope these findings contribute to a broader understanding of inference scaling laws for LLMs.

s1: Simple test-time scaling

  • https://arxiv.org/abs/2501.19393
  • Niklas Muennighoff, Zitong Yang, Weijia Shi, Xiang Lisa Li, Li Fei-Fei, Hannaneh Hajishirzi, Luke Zettlemoyer, Percy Liang, Emmanuel Candès, Tatsunori Hashimoto
  • Test-time scaling is a promising new approach to language modeling that uses extra test-time compute to improve performance. Recently, OpenAI’s o1 model showed this capability but did not publicly share its methodology, leading to many replication efforts. We seek the simplest approach to achieve test-time scaling and strong reasoning performance. First, we curate a small dataset s1K of 1,000 questions paired with reasoning traces relying on three criteria we validate through ablations: difficulty, diversity, and quality. Second, we develop budget forcing to control test-time compute by forcefully terminating the model’s thinking process or lengthening it by appending “Wait” multiple times to the model’s generation when it tries to end. This can lead the model to double-check its answer, often fixing incorrect reasoning steps. After supervised finetuning the Qwen2.5-32B-Instruct language model on s1K and equipping it with budget forcing, our model s1-32B exceeds o1-preview on competition math questions by up to 27% (MATH and AIME24). Further, scaling s1-32B with budget forcing allows extrapolating beyond its performance without test-time intervention: from 50% to 57% on AIME24. Our model, data, and code are open-source at this https URL

More Readings:


Please click each post's URL shown below to check out its full contents.

30.Model serving - Efficiency + PPO

  • Team: team-6
Customization Serving

Summary of Post :

Required Readings:

A Survey on Model Compression for Large Language Models

  • [Submitted on 15 Aug 2023 (v1), last revised 30 Jul 2024 (this version, v4)]
  • Xunyu Zhu, Jian Li, Yong Liu, Can Ma, Weiping Wang
  • https://arxiv.org/abs/2308.07633
  • Large Language Models (LLMs) have transformed natural language processing tasks successfully. Yet, their large size and high computational needs pose challenges for practical use, especially in resource-limited settings. Model compression has emerged as a key research area to address these challenges. This paper presents a survey of model compression techniques for LLMs. We cover methods like quantization, pruning, and knowledge distillation, highlighting recent advancements. We also discuss benchmarking strategies and evaluation metrics crucial for assessing compressed LLMs. This survey offers valuable insights for researchers and practitioners, aiming to enhance efficiency and real-world applicability of LLMs while laying a foundation for future advancements. Comments: Accepted for publication in TACL; a pre-MIT Press publication version

Efficient AI in Practice: Training and Deployment of Efficient LLMs for Industry Applications

  • https://arxiv.org/abs/2502.14305
  • Large language models (LLMs) have demonstrated remarkable performance across a wide range of industrial applications, from search and recommendations to generative tasks. Although scaling laws indicate that larger models generally yield better generalization and performance, their substantial computational requirements often render them impractical for many real-world scenarios at scale. In this paper, we present methods and insights for training small language models (SLMs) that deliver high performance and efficiency in deployment. We focus on two key techniques: (1) knowledge distillation and (2) model compression via quantization and pruning. These approaches enable SLMs to retain much of the quality of their larger counterparts while significantly reducing training, serving costs, and latency. We detail the impact of these techniques on a variety of use cases at a large professional social network platform and share deployment lessons - including hardware optimization strategies that enhance speed and throughput for both predictive and reasoning-based applications.

Keep the Cost Down: A Review on Methods to Optimize LLM’ s KV-Cache Consumption

  • [Submitted on 25 Jul 2024 (v1), last revised 20 Nov 2024 (this version, v4)]
  • Luohe Shi, Hongyi Zhang, Yao Yao, Zuchao Li, Hai Zhao
  • Large Language Models (LLMs), epitomized by ChatGPT’s release in late 2022, have revolutionized various industries with their advanced language comprehension. However, their efficiency is challenged by the Transformer architecture’s struggle with handling long texts. KV Cache has emerged as a pivotal solution to this issue, converting the time complexity of token generation from quadratic to linear, albeit with increased GPU memory overhead proportional to conversation length. With the development of the LLM community and academia, various KV Cache compression methods have been proposed. In this review, we dissect the various properties of KV Cache and elaborate on various methods currently used to optimize the KV Cache space usage of LLMs. These methods span the pre-training phase, deployment phase, and inference phase, and we summarize the commonalities and differences among these methods. Additionally, we list some metrics for evaluating the long-text capabilities of large language models, from both efficiency and capability perspectives. Our review thus sheds light on the evolving landscape of LLM optimization, offering insights into future advancements in this dynamic field. Links to the papers mentioned in this review can be found in our Github Repo this https URL.

PPO readings

Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study

  • Shusheng Xu, Wei Fu, Jiaxuan Gao, Wenjie Ye, Weilin Liu, Zhiyu Mei, Guangju Wang, Chao Yu, Yi Wu
  • [Submitted on 16 Apr 2024 (v1), last revised 10 Oct 2024 (this version, v3)]
  • Reinforcement Learning from Human Feedback (RLHF) is currently the most widely used method to align large language models (LLMs) with human preferences. Existing RLHF methods can be roughly categorized as either reward-based or reward-free. Novel applications such as ChatGPT and Claude leverage reward-based methods that first learn a reward model and apply actor-critic algorithms, such as Proximal Policy Optimization (PPO). However, in academic benchmarks, state-of-the-art results are often achieved via reward-free methods, such as Direct Preference Optimization (DPO). Is DPO truly superior to PPO? Why does PPO perform poorly on these benchmarks? In this paper, we first conduct both theoretical and empirical studies on the algorithmic properties of DPO and show that DPO may have fundamental limitations. Moreover, we also comprehensively examine PPO and reveal the key factors for the best performances of PPO in fine-tuning LLMs. Finally, we benchmark DPO and PPO across a collection of RLHF testbeds, ranging from dialogue to code generation. Experiment results demonstrate that PPO is able to surpass other alignment methods in all cases and achieve state-of-the-art results in challenging code competitions. Our code is publicly available at this https URL.

more readings

Generative AI on the Edge: Architecture and Performance Evaluation

  • Zeinab Nezami, Maryam Hafeez, Karim Djemame, Syed Ali Raza Zaidi
  • [Submitted on 18 Nov 2024]
  • 6G’s AI native vision of embedding advance intelligence in the network while bringing it closer to the user requires a systematic evaluation of Generative AI (GenAI) models on edge devices. Rapidly emerging solutions based on Open RAN (ORAN) and Network-in-a-Box strongly advocate the use of low-cost, off-the-shelf components for simpler and efficient deployment, e.g., in provisioning rural connectivity. In this context, conceptual architecture, hardware testbeds and precise performance quantification of Large Language Models (LLMs) on off-the-shelf edge devices remains largely unexplored. This research investigates computationally demanding LLM inference on a single commodity Raspberry Pi serving as an edge testbed for ORAN. We investigate various LLMs, including small, medium and large models, on a Raspberry Pi 5 Cluster using a lightweight Kubernetes distribution (K3s) with modular prompting implementation. We study its feasibility and limitations by analyzing throughput, latency, accuracy and efficiency. Our findings indicate that CPU-only deployment of lightweight models, such as Yi, Phi, and Llama3, can effectively support edge applications, achieving a generation throughput of 5 to 12 tokens per second with less than 50\% CPU and RAM usage. We conclude that GenAI on the edge offers localized inference in remote or bandwidth-constrained environments in 6G networks without reliance on cloud infrastructure.

Please click each post's URL shown below to check out its full contents.

31.students project presentations

  • Team: all

Summary of Post :

In this session, our readings cover:

Required Readings:

More Readings:


Please click each post's URL shown below to check out its full contents.

BackTop