解决事实核查中信息冲突问题，提升大模型判断力
Resolving Conflicting Evidence in Automated Fact-Checking: A Study on Retrieval-Augmented LLMs
- 引入外部知识检索增强大模型，应对多源信息矛盾
- 发现主流方法在处理可信度差异时表现明显下降
- 融合媒体背景信息可显著提升冲突化解能力
带有检索机制的大语言模型在事实核查任务中展现出巨大潜力，能整合外部知识。然而，当面对来自不同可信度来源的冲突证据时，其可靠性会显著下降。本文首次系统评估了在存在冲突证据的情况下，检索增强生成（RAG）模型在事实核查中的表现。为此，我们构建了名为CONFACT（Conflicting Evidence for Fact-Checking）的新数据集，包含来自不同来源的冲突信息对。大量实验揭示了当前先进RAG方法在处理因媒体可信度差异引发的冲突时存在严重缺陷。为解决该问题，我们研究了将媒体背景信息融入检索和生成阶段的策略。结果表明，有效结合来源可信度信息能显著提升RAG模型化解冲突证据的能力，从而改善事实核查性能。
原文摘要 · Abstract (English)
Large Language Models (LLMs) augmented with retrieval mechanisms have demonstrated significant potential in fact-checking tasks by integrating external knowledge. However, their reliability decreases when confronted with conflicting evidence from sources of varying credibility. This paper presents the first systematic evaluation of Retrieval-Augmented Generation (RAG) models for fact-checking in the presence of conflicting evidence. To support this study, we introduce \textbf{CONFACT} (\textbf{Con}flicting Evidence for \textbf{Fact}-Checking) (Dataset available at https://github.com/zoeyyes/CONFACT), a novel dataset comprising questions paired with conflicting information from various sources. Extensive experiments reveal critical vulnerabilities in state-of-the-art RAG methods, particularly in resolving conflicts stemming from differences in media source credibility. To address these challenges, we investigate strategies to integrate media background information into both the retrieval and generation stages. Our results show that effectively incorporating source credibility significantly enhances the ability of RAG models to resolve conflicting evidence and improve fact-checking performance.
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。