发表机构
Sungkyunkwan University; Seoul National University; University of Richmond; NAVER Cloud（成均馆大学; 首尔大学; 里士满大学; NAVER云）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出PTCG框架，结合思维树式逐步生成与剪枝及说话人人格选择，从原始论证估计作者人格并融入多样观点，以生成多样且具说服力的反论证，经多种评估验证优于基线方法。
AI 中文摘要
生成反论证的能力对于批判性思维和平衡的讨论至关重要，然而现有方法通常只生成单一的反论证，无法捕捉现实辩论中所需的多样性和说服力。为解决这一局限性，我们提出了基于人格引导的树状反论证生成（PTCG）框架，该框架结合了受思维树启发的逐步生成与剪枝以及说话人人格选择。通过从原始论证中估计作者的人格，并融入代表不同观点的说话人人格，PTCG实现了观点采择的操作化，并能够生成多样化的反论证。基于LLM作为评判者、分类器评估和人工评估的结果表明，与基线方法相比，PTCG在反论证的多样性和说服力方面均表现出一致的改进。
英文摘要
The ability to generate counterarguments is important for critical thinking and balanced discourse, yet existing approaches typically produce only a single counterargument, failing to capture the diversity and persuasiveness required in real-world debates. To address this limitation, we propose Persona-guided Tree-based Counterargument Generation (PTCG), a framework that combines Tree-of-Thoughts-inspired step-wise generation and pruning with speaker persona selection. By estimating the author's persona from the original argument and incorporating speaker personas representing distinct perspectives, PTCG operationalizes perspective-taking and enables the generation of diverse counterarguments. Results from LLM-as-a-Judge, classifier-based assessment, and human evaluations indicate that PTCG shows consistent improvements in both the diversity and persuasiveness of counterarguments compared to baseline methods.
CommentsAccepted to Findings of EMNLP 2026. 30 pages, 13 figures, 15 tables
