PaperScope
LIVE · 2026-09-09 05:40 UTC

PTCG: Persona-guided Tree-based Counterargument Generation

Eunbeen Son, Yohan Jo, Joonsuk Park, JinYeong Bak

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.07120 v1
Category
Submitted
2026-09-07

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.

Comment: Accepted to Findings of EMNLP 2026. 30 pages, 13 figures, 15 tables

arXiv abs page · PDF · same-day batch