让大模型自动生成问题，提升多模态事实核查效率。
Can LLMs Improve Multimodal Fact-Checking by Asking Relevant Questions?
- 用大模型生成与事实相关的提问，指导跨模态信息检索。
- 在多模态数据上，该方法显著优于传统基准方法。
- 适合需要自动化核查图文内容真实性的研究者使用。
传统事实核查依赖人工提出相关且有针对性的核查问题（FCQs），搜索证据并验证陈述的真实性。尽管大语言模型（LLMs）常被用于大规模自动化证据检索和真实性验证，但其效果受限于缺乏有效的FCQ生成能力。为弥补这一差距，本文探讨两个研究问题：(1) 大模型能否生成相关FCQ？(2) 大模型生成的FCQ能否提升多模态事实核查性能？为此，我们提出框架LRQ-FACT，利用大模型生成相关的问题以促进证据检索，并通过跨模态探查信息来增强事实核查。通过大量实验，验证了LRQ-FACT能够生成多种类型的相关问题，并在多模态事实核查任务中持续超越基线方法。进一步分析揭示了框架各组件如何协同提升核查表现。
原文摘要 · Abstract (English)
Traditional fact-checking relies on humans to formulate relevant and targeted fact-checking questions (FCQs), search for evidence, and verify the factuality of claims. While Large Language Models (LLMs) have been commonly used to automate evidence retrieval and factuality verification at scale, their effectiveness for fact-checking is hindered by the absence of FCQ formulation. To bridge this gap, we seek to answer two research questions: (1) Can LLMs generate relevant FCQs? (2) Can LLM-generated FCQs improve multimodal fact-checking? We therefore introduce a framework LRQ-FACT for using LLMs to generate relevant FCQs to facilitate evidence retrieval and enhance fact-checking by probing information across multiple modalities. Through extensive experiments, we verify if LRQ-FACT can generate relevant FCQs of different types and if LRQ-FACT can consistently outperform baseline methods in multimodal fact-checking. Further analysis illustrates how each component in LRQ-FACT works toward improving the 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。