PTCG: Persona-guided Tree-based Counterargument Generation

• URL: http://arxiv.org/abs/2609.07120v1
• Date: Mon, 07 Sep 2026 07:04:28 GMT
• Title: PTCG: Persona-guided Tree-based Counterargument Generation
• Abstract summary: Persona-guided Tree-based Counterargument Generation (PTCG) is a framework that combines Tree-of-Thoughts-inspired step-wise generation and pruning with speaker persona selection.<n> PTCG shows consistent improvements in both the diversity and persuasiveness of counterarguments compared to baseline methods.
• Score: 26.21869146740197
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• PERSPECTRA: A Scalable and Configurable Pluralist Benchmark of Perspectives from Arguments [16.8677147128948]
  PERSPECTRA is a pluralist benchmark for evaluating how well models represent, distinguish, and reason over multiple perspectives.<n>We construct 3,810 enriched arguments spanning 762 pro/con stances on 100 controversial topics.<n>Each opinion is expanded to multiple naturalistic variants, enabling robust evaluation of pluralism.
  arXiv  Detail & Related papers  (2026-02-09T14:25:07Z)
• SAD: A Large-Scale Strategic Argumentative Dialogue Dataset [60.33125467375306]
  In practice, argumentation is often realized as multi-turn dialogue.<n>We present the first large-scale textbfStrategic textbfArgumentative textbfDialogue dataset, consisting of 392,822 examples.
  arXiv  Detail & Related papers  (2026-01-12T11:11:37Z)
• Debating for Better Reasoning: An Unsupervised Multimodal Approach [56.74157117060815]
  We extend the debate paradigm to a multimodal setting, exploring its potential for weaker models to supervise and enhance the performance of stronger models.<n>We focus on visual question answering (VQA), where two "sighted" expert vision-language models debate an answer, while a "blind" (text-only) judge adjudicates based solely on the quality of the arguments.<n>In our framework, the experts defend only answers aligned with their beliefs, thereby obviating the need for explicit role-playing and concentrating the debate on instances of expert disagreement.
  arXiv  Detail & Related papers  (2025-05-20T17:18:17Z)
• "Reasoning" with Rhetoric: On the Style-Evidence Tradeoff in LLM-Generated Counter-Arguments [11.243184875465788]
  Large language models (LLMs) play a key role in generating evidence-based and stylistic counter-arguments.<n>Previous research often neglects the balance between evidentiality and style, which are crucial for persuasive arguments.<n>We evaluated the effectiveness of stylized evidence-based counter-argument generation in Counterfire, a new dataset of 38,000 counter-arguments.
  arXiv  Detail & Related papers  (2024-02-13T14:53:12Z)
• Argue with Me Tersely: Towards Sentence-Level Counter-Argument Generation [62.069374456021016]
  We present the ArgTersely benchmark for sentence-level counter-argument generation. We also propose Arg-LlaMA for generating high-quality counter-argument.
  arXiv  Detail & Related papers  (2023-12-21T06:51:34Z)
• A Unifying Framework for Learning Argumentation Semantics [47.84663434179473]
  We present a novel framework, which uses an Inductive Logic Programming approach to learn the acceptability semantics for several abstract and structured argumentation frameworks in an interpretable way.<n>Our framework outperforms existing argumentation solvers, thus opening up new future research directions in the area of formal argumentation and human-machine dialogues.
  arXiv  Detail & Related papers  (2023-10-18T20:18:05Z)
• Conclusion-based Counter-Argument Generation [26.540485804067536]
  In real-world debates, the most common way to counter an argument is to reason against its main point, that is, its conclusion. We propose a multitask approach that jointly learns to generate both the conclusion and the counter of an input argument.
  arXiv  Detail & Related papers  (2023-01-24T10:49:01Z)
• Persua: A Visual Interactive System to Enhance the Persuasiveness of Arguments in Online Discussion [52.49981085431061]
  Enhancing people's ability to write persuasive arguments could contribute to the effectiveness and civility in online communication. We derived four design goals for a tool that helps users improve the persuasiveness of arguments in online discussions. Persua is an interactive visual system that provides example-based guidance on persuasive strategies to enhance the persuasiveness of arguments.
  arXiv  Detail & Related papers  (2022-04-16T08:07:53Z)
• Exploring the Role of Argument Structure in Online Debate Persuasion [39.74040217761505]
  We investigate the role of discourse structure of the arguments from online debates in their persuasiveness. We find that argument structure features play an essential role in achieving the better predictive performance.
  arXiv  Detail & Related papers  (2020-10-07T17:34:50Z)
• Aspect-Controlled Neural Argument Generation [65.91772010586605]
  We train a language model for argument generation that can be controlled on a fine-grained level to generate sentence-level arguments for a given topic, stance, and aspect. Our evaluation shows that our generation model is able to generate high-quality, aspect-specific arguments. These arguments can be used to improve the performance of stance detection models via data augmentation and to generate counter-arguments.
  arXiv  Detail & Related papers  (2020-04-30T20:17:22Z)
• You Impress Me: Dialogue Generation via Mutual Persona Perception [62.89449096369027]
  The research in cognitive science suggests that understanding is an essential signal for a high-quality chit-chat conversation. Motivated by this, we propose P2 Bot, a transmitter-receiver based framework with the aim of explicitly modeling understanding.
  arXiv  Detail & Related papers  (2020-04-11T12:51:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.