Persuasion Should be Double-Blind: A Multi-Domain Dialogue Dataset With Faithfulness Based on Causal Theory of Mind
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918519623385088 |
|---|---|
| author | Zhang, Dingyi Zhang, Linhai Qu, Fanglei Zhuang, Ziqing Zhou, Deyu |
| author_facet | Zhang, Dingyi Zhang, Linhai Qu, Fanglei Zhuang, Ziqing Zhou, Deyu |
| contents | Persuasive dialogue is central to human communication, yet existing datasets often rely on a single language model generating both roles, producing unrealistic interactions that violate the double-blind nature of persuasion. To overcome this, we propose ToMMA, a multi-agent framework guided by causal Theory of Mind that enforces role separation and prevents information leakage. Using ToMMA, we build CToMPersu, a large-scale multi-turn, multi-domain dataset capturing realistic persuasion dynamics. Automatic evaluations show that CToMPersu produces more coherent and persuasive dialogues than prior datasets. Furthermore, when used as a knowledge base, CToMPersu significantly enhances the persuasive performance of large language models, as confirmed by both automatic and human evaluations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_21297 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Persuasion Should be Double-Blind: A Multi-Domain Dialogue Dataset With Faithfulness Based on Causal Theory of Mind Zhang, Dingyi Zhang, Linhai Qu, Fanglei Zhuang, Ziqing Zhou, Deyu Computation and Language Persuasive dialogue is central to human communication, yet existing datasets often rely on a single language model generating both roles, producing unrealistic interactions that violate the double-blind nature of persuasion. To overcome this, we propose ToMMA, a multi-agent framework guided by causal Theory of Mind that enforces role separation and prevents information leakage. Using ToMMA, we build CToMPersu, a large-scale multi-turn, multi-domain dataset capturing realistic persuasion dynamics. Automatic evaluations show that CToMPersu produces more coherent and persuasive dialogues than prior datasets. Furthermore, when used as a knowledge base, CToMPersu significantly enhances the persuasive performance of large language models, as confirmed by both automatic and human evaluations. |
| title | Persuasion Should be Double-Blind: A Multi-Domain Dialogue Dataset With Faithfulness Based on Causal Theory of Mind |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2502.21297 |