具备可解释推理的医疗声明逐步事实验证系统
Step-by-Step Fact Verification System for Medical Claims with Explainable Reasoning
AI总结：
针对医疗领域事实验证缺乏探索的问题，本研究将基于LLM的迭代式逐步验证系统应用于三个医疗数据集，通过多设置评估证明其性能优于传统方法，为领域专用验证提供新思路。
摘要：
事实验证（FV）旨在依据相关证据评估声明的真实性。传统自动事实验证方法采用三阶段流水线，依赖短证据片段和仅编码器的推理模型。近期方法利用大语言模型（LLM）的多轮交互特性，将事实验证视为逐步求解的问题：生成用于询问额外上下文的问题并作答，直至信息充足以做出决策。这种迭代方法让验证过程具备合理性与可解释性。现有方法已在百科类声明上完成测试，但缺乏针对特定领域真实场景声明的探索。本研究将迭代式事实验证系统应用于三个医疗事实验证数据集，并在多种设置下开展评估，涵盖不同LLM、外部网页搜索以及基于逻辑谓词的结构化推理。结果表明，该方法相较传统方法在最终性能上有所提升，逐步事实验证系统在特定领域声明验证中具备很高潜力。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
