用分步推理验证医疗声明真伪，提升可解释性。
Step-by-Step Fact Verification System for Medical Claims with Explainable Reasoning
- 通过多轮提问与回答逐步获取证据，实现可解释的验证过程。
- 在三个医疗数据集上表现优于传统方法，准确率显著提升。
- 适合医学领域专家和需要透明决策的AI应用。
事实验证（FV）旨在基于相关证据评估声明的真实性。传统自动化FV采用三阶段流水线，依赖短证据片段和编码器模型。近期方法利用大语言模型（LLM）的多轮交互特性，将FV视为分步问题：通过生成并回答追问以获取更多上下文，直至做出判断。该迭代方法使验证过程更具逻辑性和可解释性。尽管此类方法已在百科类声明上测试，但对领域特定且真实的声明仍缺乏探索。本文将迭代FV系统应用于三个医疗事实核查数据集，评估了多种设置下的表现，包括不同LLM、外部网络搜索及基于逻辑谓词的结构化推理。结果表明，该方法在最终性能上超越传统方案，展现出针对领域特定声明的强大潜力。
原文摘要 · Abstract (English)
Fact verification (FV) aims to assess the veracity of a claim based on relevant evidence. The traditional approach for automated FV includes a three-part pipeline relying on short evidence snippets and encoder-only inference models. More recent approaches leverage the multi-turn nature of LLMs to address FV as a step-by-step problem where questions inquiring additional context are generated and answered until there is enough information to make a decision. This iterative method makes the verification process rational and explainable. While these methods have been tested for encyclopedic claims, exploration on domain-specific and realistic claims is missing. In this work, we apply an iterative FV system on three medical fact-checking datasets and evaluate it with multiple settings, including different LLMs, external web search, and structured reasoning using logic predicates. We demonstrate improvements in the final performance over traditional approaches and the high potential of step-by-step FV systems for domain-specific claims.
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。