让AI从不同角色视角生成多样且有说服力的反驳意见
PTCG: Persona-guided Tree-based Counterargument Generation
- 基于思维树逐步生成并筛选反驳观点
- 生成的反驳意见在多样性与说服力上均优于基线
- 适合需要多角度思辨的对话系统与教育场景
生成反驳意见对批判性思维和平衡讨论至关重要，但现有方法通常只产生单一反驳，难以满足真实辩论中所需的观点多样性与说服力。为此，我们提出人物引导的树状反驳生成框架（PTCG），结合受思维树启发的分步生成与剪枝策略，并引入代表不同立场的说话人角色。通过从原论点推断作者角色，并融合体现多元视角的说话人角色，PTCG实现了视角代入，推动生成多样化反驳。基于大模型评分、分类器评估及人工评价的结果显示，相比基线方法，PTCG在反驳意见的多样性与说服力上均有稳定提升。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。