Enregistré dans:
Détails bibliographiques
Auteurs principaux: Nozue, Shinnosuke, Nakano, Yuto, Watanabe, Yotaro, Takasaki, Meguru, Moriya, Shoji, Akama, Reina, Suzuki, Jun
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2602.22696
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911470126628864
author Nozue, Shinnosuke
Nakano, Yuto
Watanabe, Yotaro
Takasaki, Meguru
Moriya, Shoji
Akama, Reina
Suzuki, Jun
author_facet Nozue, Shinnosuke
Nakano, Yuto
Watanabe, Yotaro
Takasaki, Meguru
Moriya, Shoji
Akama, Reina
Suzuki, Jun
contents Current approaches to developing persuasive dialogue agents often rely on a limited set of predefined persuasive strategies that fail to capture the complexity of real-world interactions. We applied a cross-disciplinary approach to develop a framework for designing persuasive dialogue agents that draws on proven strategies from social psychology, behavioral economics, and communication theory. We validated our proposed framework through experiments on two distinct datasets: the Persuasion for Good dataset, which represents a specific in-domain scenario, and the DailyPersuasion dataset, which encompasses a wide range of scenarios. The proposed framework achieved strong results for both datasets and demonstrated notable improvement in the persuasion success rate as well as promising generalizability. Notably, the proposed framework also excelled at persuading individuals with initially low intent, which addresses a critical challenge for persuasive dialogue agents.
format Preprint
id arxiv_https___arxiv_org_abs_2602_22696
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Enhancing Persuasive Dialogue Agents by Synthesizing Cross-Disciplinary Communication Strategies
Nozue, Shinnosuke
Nakano, Yuto
Watanabe, Yotaro
Takasaki, Meguru
Moriya, Shoji
Akama, Reina
Suzuki, Jun
Computation and Language
Current approaches to developing persuasive dialogue agents often rely on a limited set of predefined persuasive strategies that fail to capture the complexity of real-world interactions. We applied a cross-disciplinary approach to develop a framework for designing persuasive dialogue agents that draws on proven strategies from social psychology, behavioral economics, and communication theory. We validated our proposed framework through experiments on two distinct datasets: the Persuasion for Good dataset, which represents a specific in-domain scenario, and the DailyPersuasion dataset, which encompasses a wide range of scenarios. The proposed framework achieved strong results for both datasets and demonstrated notable improvement in the persuasion success rate as well as promising generalizability. Notably, the proposed framework also excelled at persuading individuals with initially low intent, which addresses a critical challenge for persuasive dialogue agents.
title Enhancing Persuasive Dialogue Agents by Synthesizing Cross-Disciplinary Communication Strategies
topic Computation and Language
url https://arxiv.org/abs/2602.22696