Persona guided method creates diverse counterarguments for debates
PTCG: Persona-guided Tree-based Counterargument Generation
Computation and Language
Summary
People often need multiple reasons to disagree with a point in a conversation, but most current computer programs can only create one counterargument at a time. The authors developed a new system called PTCG that uses different personality perspectives and builds counterarguments step-by-step like a decision tree. This approach helps create many different and convincing counterarguments instead of just one. Tests with both humans and automated tools showed that PTCG makes more varied and persuasive responses compared to older methods.
counterargumentcritical thinkingpersonatree of thoughtslarge language modelperspective takingargument generationdiversitypersuasivenesshuman evaluation
Authors
Eunbeen Son, Yohan Jo, Joonsuk Park, JinYeong Bak
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.