通过建模事实级冲突，让大模型更忠实于检索内容。
FaithfulRAG: Fact-Level Conflict Modeling for Context-Faithful Retrieval-Augmented Generation
- 在事实层面识别检索内容与模型知识的冲突
- 设计自思考机制，先推理再生成响应
- 适合需要高可信度问答的场景
增强检索的大语言模型在处理知识密集型任务时展现出巨大潜力，但常出现生成内容不忠实的问题：或忽略检索信息，或不一致地融合模型内部知识。尤其当检索内容与模型参数知识存在冲突时，问题更严重。现有方法通过提示工程或解码策略强制遵循检索内容，却会压制模型自身知识，破坏其内部结构并增加误解风险。为此，本文提出FaithfulRAG，一种新框架，通过显式建模模型参数知识与检索内容之间的差异来解决冲突。具体而言，该方法在事实层面识别冲突，并引入自思考过程，使大模型能先推理冲突事实，再生成答案。大量实验表明，该方法优于当前最先进方法。代码已开源：https://github.com/DeepLearnXMU/Faithful-RAG。
原文摘要 · Abstract (English)
Large language models (LLMs) augmented with retrieval systems have demonstrated significant potential in handling knowledge-intensive tasks. However, these models often struggle with unfaithfulness issues, generating outputs that either ignore the retrieved context or inconsistently blend it with the LLM`s parametric knowledge. This issue is particularly severe in cases of knowledge conflict, where the retrieved context conflicts with the model`s parametric knowledge. While existing faithful RAG approaches enforce strict context adherence through well-designed prompts or modified decoding strategies, our analysis reveals a critical limitation: they achieve faithfulness by forcibly suppressing the model`s parametric knowledge, which undermines the model`s internal knowledge structure and increases the risk of misinterpreting the context. To this end, this paper proposes FaithfulRAG, a novel framework that resolves knowledge conflicts by explicitly modeling discrepancies between the model`s parametric knowledge and retrieved context. Specifically, FaithfulRAG identifies conflicting knowledge at the fact level and designs a self-thinking process, allowing LLMs to reason about and integrate conflicting facts before generating responses. Extensive experiments demonstrate that our method outperforms state-of-the-art methods. The code is available at https://github.com/DeepLearnXMU/Faithful-RAG
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。