# Synthetic Socratic Debates: Examining Persona Effects on Moral Decision and Persuasion Dynamics

arXiv: https://arxiv.org/abs/2506.12657 · HTML: https://mlsanity.com/paper/2506.12657/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 103 references that are in the map.
- First posted on arXiv 14 Jun 2025.

## Builds on (most cited first, 30 of 36)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Toxicity in ChatGPT: Analyzing Persona-assigned Language Models](https://mlsanity.com/paper/2304.05335/) (2023)
- [Character-LLM: A Trainable Agent for Role-Playing](https://mlsanity.com/paper/2310.10158/) (2023)
- [ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs](https://mlsanity.com/paper/2309.13007/) (2023)
- [Role-Play with Large Language Models](https://mlsanity.com/paper/2305.16367/) (2023)
- [Social Chemistry 101: Learning to Reason about Social and Moral Norms](https://mlsanity.com/paper/2011.00620/) (2020)
- [Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs](https://mlsanity.com/paper/2311.04892/) (2023)
- [The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientation](https://mlsanity.com/paper/2301.01768/) (2023)
- [Quantifying the Persona Effect in LLM Simulations](https://mlsanity.com/paper/2402.10811/) (2024)
- [Investigating Cultural Alignment of Large Language Models](https://mlsanity.com/paper/2402.13231/) (2024)
- [Collective Constitutional AI: Aligning a Language Model with Public Input](https://mlsanity.com/paper/2406.07814/) (2024)
- [Winning Arguments: Interaction Dynamics and Persuasion Strategies in Good-faith Online Discussions](https://mlsanity.com/paper/1602.01103/) (2016)
- [Scruples: A Corpus of Community Ethical Judgments on 32,000 Real-Life Anecdotes](https://mlsanity.com/paper/2008.09094/) (2020)
- [Can ChatGPT Defend its Belief in Truth? Evaluating LLM Reasoning via Debate](https://mlsanity.com/paper/2305.13160/) (2023)
- [Evaluating Large Language Model Biases in Persona-Steered Generation](https://mlsanity.com/paper/2405.20253/) (2024)
- [DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life](https://mlsanity.com/paper/2410.02683/) (2024)
- [BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Data](https://mlsanity.com/paper/2410.16491/) (2024)
- [Language Model Alignment in Multilingual Trolley Problems](https://mlsanity.com/paper/2407.02273/) (2024)
- [AMPERSAND: Argument Mining for PERSuAsive oNline Discussions](https://mlsanity.com/paper/2004.14677/) (2020)
- [Beyond Demographics: Aligning Role-playing LLM-based Agents Using Human Belief Networks](https://mlsanity.com/paper/2406.17232/) (2024)
- [Large Language Models are as persuasive as humans, but how? About the cognitive effort and moral-emotional language of LLM arguments](https://mlsanity.com/paper/2404.09329/) (2024)
- [Debate-to-Write: A Persona-Driven Multi-Agent Framework for Diverse Argument Generation](https://mlsanity.com/paper/2406.19643/) (2024)
- [How Susceptible are Large Language Models to Ideological Manipulation?](https://mlsanity.com/paper/2402.11725/) (2024)
- [Debatrix: Multi-dimensional Debate Judge with Iterative Chronological Analysis Based on LLM](https://mlsanity.com/paper/2403.08010/) (2024)
- [Implicit Personalization in Language Models: A Systematic Study](https://mlsanity.com/paper/2405.14808/) (2024)
- [Plurals: A System for Guiding LLMs Via Simulated Social Ensembles](https://mlsanity.com/paper/2409.17213/) (2024)
- [Unmasking Conversational Bias in AI Multiagent Systems](https://mlsanity.com/paper/2501.14844/) (2025)
- [When Ethics and Payoffs Diverge: LLM Agents in Morally Charged Social Dilemmas](https://mlsanity.com/paper/2505.19212/) (2025)
- [Must Read: A Comprehensive Survey of Computational Persuasion](https://mlsanity.com/paper/2505.07775/) (2025)
- [The Staircase of Ethics: Probing LLM Value Priorities through Multi-Step Induction to Complex Moral Dilemmas](https://mlsanity.com/paper/2505.18154/) (2025)

## Built on by (most cited first, 19 of 19)

- [Accumulating Context Changes the Beliefs of Language Models](https://mlsanity.com/paper/2511.01805/) (2025)
- [When Identity Skews Debate: Anonymization for Bias-Reduced Multi-Agent Reasoning](https://mlsanity.com/paper/2510.07517/) (2025)
- [Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems](https://mlsanity.com/paper/2602.15198/) (2026)
- [Humanizing Machines: Rethinking LLM Anthropomorphism Through a Multi-Level Framework of Design](https://mlsanity.com/paper/2508.17573/) (2025)
- [The Chameleon's Limit: Investigating Persona Collapse and Homogenization in Large Language Models](https://mlsanity.com/paper/2604.24698/) (2026)
- [Personalization Increases Affective Alignment but Has Role-Dependent Effects on Epistemic Independence in LLMs](https://mlsanity.com/paper/2603.00024/) (2026)
- [Interaction Protocol Shapes Moral Judgment in Multi-Agent Debate](https://mlsanity.com/paper/2510.10002/) (2025)
- [Love First, Know Later: Persona-Based Romantic Compatibility Through LLM Text World Engines](https://mlsanity.com/paper/2512.11844/) (2025)
- [Culturally Grounded Personas in Large Language Models: Characterization and Alignment with Socio-Psychological Value Frameworks](https://mlsanity.com/paper/2601.22396/) (2026)
- [Evaluating Cooperation in LLM Social Groups through Elected Leadership](https://mlsanity.com/paper/2604.11721/) (2026)
- [Large language models show fragile cognitive reasoning about human emotions](https://mlsanity.com/paper/2508.05880/) (2025)
- [Sentipolis: Emotion-Aware Agents for Social Simulations](https://mlsanity.com/paper/2601.18027/) (2026)
- [Re-Centering Humans in LLM Personalization](https://mlsanity.com/paper/2606.06614/) (2026)
- [Every Act Has Its Price: Compressed Moral Composition in Frontier LLMs](https://mlsanity.com/paper/2606.11232/) (2026)
- [PersonaTeaming: Supporting Persona-Driven Red-Teaming for Generative AI](https://mlsanity.com/paper/2605.05682/) (2026)
- [LLM Wardens: Mitigating Adversarial Persuasion with Third-Party Conversational Oversight](https://mlsanity.com/paper/2605.08321/) (2026)
- [Staying with the Uncertainty: Uncertainty-Scaffolding Strategies for Artificial Moral Advisors in LLM-to-LLM Simulated Conversations](https://mlsanity.com/paper/2606.05890/) (2026)
- [DLawBench: Evaluating LLMs Through Multi-Turn Legal Consultation](https://mlsanity.com/paper/2606.13931/) (2026)
- [Readable, Faithful, Used: Three Dissociable Properties of Demographic Identity in a Language Model](https://mlsanity.com/paper/2608.18768/) (2026)

## Abstract (arXiv)

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.