检索关系，检测谬误：一种用于政治辩论分析的RAG方法
Retrieving Relations, Detecting Fallacies: A RAG Approach to Political Debate Analysis
- CNRS（法国国家科学研究中心）
- INRIA（法国国家信息与自动化研究所）
- I3S（信息、信号与系统实验室）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究针对政治辩论中谬误自动检测的需求，提出引导式RAG方法，利用论证关系动态检索外部知识，在ElecDeb60to20基准上使谬误检测与分类性能显著提升。
AI中文摘要：
谬误是采用无效推理的论证，在塑造公众舆论的高风险政治辩论等敏感场景中，自动检测谬误至关重要。识别谬误论证需要超越其纯表层文本的上下文知识，包括与讨论主题相关的世界知识，以及论证话语中各论证之间存在的关系知识。此前关于谬误分析的研究表明，论证话语结构可有效提升分类性能，但这类结构通常仅被编码为静态分类器特征，灵活性受限。基于这一认知并解决该局限，我们提出一种引导式检索增强（RAG）方法用于谬误检测与分类，该方法利用支持与攻击的论证关系动态引导相关文档的提取。我们在ElecDeb60to20基准上对该方法进行评估，涉及42种检索配置和14种模型，对15GB的政治相关文档知识库进行检索。与非检索基线相比，我们的方法使谬误检测的宏F1值提升至0.864，分类的宏F1值提升至0.725。这些结果表明，当检索受到论证引导时，结合外部知识可显著提升谬误检测与分类性能。
英文摘要：
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 that exist between arguments within the argumentative discourse. Prior work on fallacy analysis has shown that argumentative discourse structure can beneficially improve classification performance. However, such structure is typically encoded only as static classifier features, limiting its flexibility. Building on this intuition while addressing this limitation, we introduce a guided retrieval-augmented methodology for fallacy detection and classification that leverages argumentative relations of support and attack to dynamically steer the extraction of relevant documents. We evaluate our approach on the ElecDeb60to20 benchmark across 42 retrieval configurations and 14 models, performing retrieval over a 15GB knowledge base of collected political-related documents. Our approach improves macro-F1 up to 0.864 for fallacy detection and up to 0.725 for classification over non-retrieval baselines. These results show that incorporating external knowledge significantly enhances fallacy detection and classification when retrieval is argumentatively guided.
