基于RAG的论证关系引导方法用于政治辩论谬误检测
原标题：Retrieving Relations, Detecting Fallacies: A RAG Approach to Political Debate Analysis
AI 摘要
该研究提出一种基于检索增强生成（RAG）的谬误检测与分类方法，利用论证关系（支持与攻击）动态引导外部知识检索，以提升政治辩论中谬误识别的准确性。在ElecDeb60to20基准上，通过42种检索配置和14个模型评估，谬误检测的macro-F1最高达0.864，分类达0.725，显著优于非检索基线。该方法构建了15GB的领域知识库，并强调论证结构作为动态检索引导而非静态特征。
正文节选
Retrieving Relations, Detecting Fallacies: A RAG Approach to Political Debate Analysis Abstract Fallacies are arguments that employ invalid reasoning, making their automatic detection critical in sensitive contexts such as high-stakes political debates, where public opinion is shaped. Spotting a fallacious argument requires contextual knowledge beyond its pure surface text. This entails world knowledge pertaining to the subject matter under discussion, as well as knowledge of the relationships t