Synthetic Socratic Debates: Examining Persona Effects on Moral Decision and Persuasion Dynamics
This work addresses the need for persona-aware evaluation frameworks in AI moral reasoning for applications in morally sensitive domains, representing an incremental advance by applying existing methods to new data.
The study investigated how persona traits in large language models affect moral reasoning and persuasion in AI-AI debates over 131 real-world moral dilemmas, finding that political ideology and personality traits most strongly influence initial stances and outcomes, with liberal and open personas achieving higher consensus and win rates.
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.