发现并解决大模型检索中信息冲突问题，提升回答准确性。
DRAGged into Conflicts: Detecting and Addressing Conflicting Sources in Search-Augmented LLMs
- 提出信息冲突分类体系与应对策略
- 构建首个带专家标注的冲突基准数据集
- 实验证明现有模型处理冲突能力弱，需改进推理机制
检索增强生成（RAG）常用于为大语言模型（LLMs）提供相关且最新的信息，但检索到的内容常存在矛盾。本文首次提出RAG中知识冲突类型的分类体系，并定义各类冲突下的理想模型行为。随后，构建了CONFLICTS——首个在真实RAG场景下具有专家标注的高质量基准数据集，支持对多种知识冲突的追踪评估。在该基准上开展大量实验表明，当前LLMs普遍难以恰当处理来源间的信息冲突。尽管通过提示模型显式推理潜在冲突可显著提升响应质量与适切性，但未来研究仍有巨大改进空间。
原文摘要 · Abstract (English)
Retrieval Augmented Generation (RAG) is a commonly used approach for enhancing large language models (LLMs) with relevant and up-to-date information. However, the retrieved sources can often contain conflicting information and it remains unclear how models should address such discrepancies. In this work, we first propose a novel taxonomy of knowledge conflict types in RAG, along with the desired model behavior for each type. We then introduce CONFLICTS, a high-quality benchmark with expert annotations of conflict types in a realistic RAG setting. CONFLICTS is the first benchmark that enables tracking progress on how models address a wide range of knowledge conflicts. We conduct extensive experiments on this benchmark, showing that LLMs often struggle to appropriately resolve conflicts between sources. While prompting LLMs to explicitly reason about the potential conflict in the retrieved documents significantly improves the quality and appropriateness of their responses, substantial room for improvement in future research remains.
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。