从论证组件到图：一种具有置信门控的多智能体辩论方法用于论证关系识别
From Argument Components to Graphs: A Multi-Agent Debate with Confidence Gating for Argument Relations
AI总结：
提出一种多智能体辩论框架，通过置信门控机制仅在不确定时进行辩论，在UKP语料上达到训练无关方法最高Macro F1，并生成可读辩论记录。
摘要：
大型语言模型（LLMs）凭借其强大的通用推理能力，在论证挖掘（AM）领域受到越来越多的评估和应用。然而，标准的无训练模型常常遗漏复杂细节，特别是在需要将文本的两个部分一起分析的上下文中。此外，自我纠正机制往往会强化推理中的初始幻觉。克服这些限制通常需要昂贵的、领域特定的监督微调。最近的研究表明，多智能体范式可以通过支持者-反对者-裁判架构的辩证改进来解决组件分类任务中的此类弱点，为该领域的无训练方法指明了有希望的方向。在本文中，我们将该框架扩展并评估于论证关系识别与分类（ARIC）任务，将其重新表述为组件对之间的辩论。此外，我们引入了一种置信门控机制，使得仅在不确定的情况下进行辩论，而在置信度高时接受初始预测。在UKP Argument Annotated Essays v2语料库上，我们证明了选择性辩论在所有无训练方法中取得了最高的Macro F1，而对所有样本进行辩论则使性能低于其中一个基线。所有生成方法在Macro F1上也优于微调的RoBERTa模型，这表明Attack类的代表性不足对监督微调的损害大于对仅推理模型的影响。此外，我们的框架生成人类可读的辩论记录，提供了单智能体和监督分类器所缺乏的可解释性。
英文摘要：
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. In this paper, we extend and evaluate this framework on the Argument Relation Identification and Classification (ARIC) task, reformulating it as a debate over component pairs. Besides that, we introduce a confidence gating mechanism that enables debating only on the uncertain cases and accepting the initial prediction when confidence is high. On the UKP Argument Annotated Essays v2 corpus, we demonstrate that the selective debate achieves the highest Macro F1 among all training-free methods, while debate over all samples degrades performance below that of one of the baselines. All generative approaches also outperform fine-tuned RoBERTa models on Macro F1, suggesting that the under-representation of the Attack class was more damaging to supervised fine-tuning than to inference-only models. Additionally, our framework produces human-readable debate transcripts, offering interpretability absent from both single-agent and supervised classifiers.
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。
