From Argument Components to Graphs: A Multi-Agent Debate with Confidence Gating for Argument Relations 文章

ArXiv CS.CL2026-06-16NEWSen作者: Jakub B\k{a}ba, Jaros{\l}aw A. Chudziak

详细信息

来源站点
ArXiv CS.CL
作者
Jakub B\k{a}ba, Jaros{\l}aw A. Chudziak
文章类型
NEWS
语言
en
发布日期
2026-06-16

摘要

arXiv:2606.16047v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly assessed and utilized in the field of Argument Mining (AM), thanks to their strong general reasoning capabilities. However, standard training-free models often miss sophisticated details, specifically in contexts where two parts of the text have to be analyzed together. Furthermore, self-correction mechanisms tend to reinforce initial hallucinations in reasoning. Overcoming these limitations typically requires expensive, domain-specific supervised fine-tuning. Recent work has shown that a multi-agent paradigm can address such weaknesses for the component classification task through dialectical refinement with a Proponent-Opponent-Judge architecture, setting a promising direction for training-free approaches in the field.