Platform - long context vs RAG + Hallucination

• Lead team: team-2

RAG LongContext

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.