研究大模型如何忠实利用外部信息，发现记忆强弱和证据风格影响其采纳程度。
Investigating Context-Faithfulness in Large Language Models: The Roles of Memory Strength and Evidence Style
- 用问题改写后的响应差异衡量模型记忆强度，新方法更精准。
- 记忆越强的问题，模型越依赖内部知识而非外部证据。
- 改写过的证据比重复或加细节更能提升模型对外部信息的接受度。
检索增强生成（RAG）通过在生成过程中引入外部信息来提升大语言模型（LLMs）的表现。然而，模型对上下文的忠实程度及其影响因素仍不明确。本研究探讨了记忆强度和证据呈现方式对模型采纳外部信息的影响。通过测量同一问题不同改写版本下模型响应的差异，量化其记忆强度，该方法未被先前工作采用。同时，生成多种风格的证据以考察模型行为。结果显示，对于记忆强度高的问题，模型更倾向于依赖内部记忆；而相较于简单重复或添加细节，改写形式的证据能显著提升模型对外部信息的接纳度。这些发现为改进检索增强生成与上下文感知型大模型提供了关键洞见。代码已开源：https://github.com/liyp0095/ContextFaithful。
原文摘要 · Abstract (English)
Retrieval-augmented generation (RAG) improves Large Language Models (LLMs) by incorporating external information into the response generation process. However, how context-faithful LLMs are and what factors influence LLMs' context faithfulness remain largely unexplored. In this study, we investigate the impact of memory strength and evidence presentation on LLMs' receptiveness to external evidence. We quantify the memory strength of LLMs by measuring the divergence in LLMs' responses to different paraphrases of the same question, which is not considered by previous works. We also generate evidence in various styles to examine LLMs' behavior. Our results show that for questions with high memory strength, LLMs are more likely to rely on internal memory. Furthermore, presenting paraphrased evidence significantly increases LLMs' receptiveness compared to simple repetition or adding details. These findings provide key insights for improving retrieval-augmented generation and context-aware LLMs. Our code is available at https://github.com/liyp0095/ContextFaithful.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。