Synthetic Socratic Debates: Examining Persona Effects on Moral Decision and Persuasion Dynamics
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912860475490304 |
|---|---|
| author | Liu, Jiarui Song, Yueqi Xiao, Yunze Zheng, Mingqian Tjuatja, Lindia Borg, Jana Schaich Diab, Mona Sap, Maarten |
| author_facet | Liu, Jiarui Song, Yueqi Xiao, Yunze Zheng, Mingqian Tjuatja, Lindia Borg, Jana Schaich Diab, Mona Sap, Maarten |
| contents | As large language models (LLMs) are increasingly used in morally sensitive domains, it is crucial to understand how persona traits affect their moral reasoning and persuasive behavior. We present the first large-scale study of multi-dimensional persona effects in AI-AI debates over real-world moral dilemmas. Using a 6-dimensional persona space (age, gender, country, class, ideology, and personality), we simulate structured debates between AI agents over 131 relationship-based cases. Our results show that personas affect initial moral stances and debate outcomes, with political ideology and personality traits exerting the strongest influence. Persuasive success varies across traits, with liberal and open personalities reaching higher consensus and win rates. While logit-based confidence grows during debates, emotional and credibility-based appeals diminish, indicating more tempered argumentation over time. These trends mirror findings from psychology and cultural studies, reinforcing the need for persona-aware evaluation frameworks for AI moral reasoning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_12657 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Synthetic Socratic Debates: Examining Persona Effects on Moral Decision and Persuasion Dynamics Liu, Jiarui Song, Yueqi Xiao, Yunze Zheng, Mingqian Tjuatja, Lindia Borg, Jana Schaich Diab, Mona Sap, Maarten Computation and Language As large language models (LLMs) are increasingly used in morally sensitive domains, it is crucial to understand how persona traits affect their moral reasoning and persuasive behavior. We present the first large-scale study of multi-dimensional persona effects in AI-AI debates over real-world moral dilemmas. Using a 6-dimensional persona space (age, gender, country, class, ideology, and personality), we simulate structured debates between AI agents over 131 relationship-based cases. Our results show that personas affect initial moral stances and debate outcomes, with political ideology and personality traits exerting the strongest influence. Persuasive success varies across traits, with liberal and open personalities reaching higher consensus and win rates. While logit-based confidence grows during debates, emotional and credibility-based appeals diminish, indicating more tempered argumentation over time. These trends mirror findings from psychology and cultural studies, reinforcing the need for persona-aware evaluation frameworks for AI moral reasoning. |
| title | Synthetic Socratic Debates: Examining Persona Effects on Moral Decision and Persuasion Dynamics |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2506.12657 |