mlsanityData to 14 Oct 2026

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

arXiv 2506.12657 ↗First posted 14 Jun 2025cs.CLcited by 19

Not on the map. Why?

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.

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

36 of 103 references.

References · 36

  1. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  2. 2023Toxicity in ChatGPT: Analyzing Persona-assigned Language Modelscited by 360
  3. 2023Character-LLM: A Trainable Agent for Role-Playingcited by 339
  4. 2023ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMscited by 309
  5. 2023Role-Play with Large Language Modelscited by 294
  6. 2020Social Chemistry 101: Learning to Reason about Social and Moral Normscited by 255
  7. 2023Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMscited by 199
  8. 2023The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientationcited by 189
  9. 2024Quantifying the Persona Effect in LLM Simulationscited by 169
  10. 2024Investigating Cultural Alignment of Large Language Modelscited by 143
  11. 2024Collective Constitutional AI: Aligning a Language Model with Public Inputcited by 123
  12. 2016Winning Arguments: Interaction Dynamics and Persuasion Strategies in Good-faith Online Discussionscited by 110
24 more
  1. 2020Scruples: A Corpus of Community Ethical Judgments on 32,000 Real-Life Anecdotescited by 101
  2. 2023Can ChatGPT Defend its Belief in Truth? Evaluating LLM Reasoning via Debatecited by 94
  3. 2024Evaluating Large Language Model Biases in Persona-Steered Generationcited by 78
  4. 2024DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Lifecited by 59
  5. 2024BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Datacited by 50
  6. 2024Language Model Alignment in Multilingual Trolley Problemscited by 46
  7. 2020AMPERSAND: Argument Mining for PERSuAsive oNline Discussionscited by 39
  8. 2024Beyond Demographics: Aligning Role-playing LLM-based Agents Using Human Belief Networkscited by 39
  9. 2024Large Language Models are as persuasive as humans, but how? About the cognitive effort and moral-emotional language of LLM argumentscited by 30
  10. 2024Debate-to-Write: A Persona-Driven Multi-Agent Framework for Diverse Argument Generationcited by 29
  11. 2024How Susceptible are Large Language Models to Ideological Manipulation?cited by 26
  12. 2024Debatrix: Multi-dimensional Debate Judge with Iterative Chronological Analysis Based on LLMcited by 21
  13. 2024Implicit Personalization in Language Models: A Systematic Studycited by 18
  14. 2024Plurals: A System for Guiding LLMs Via Simulated Social Ensemblescited by 17
  15. 2025Unmasking Conversational Bias in AI Multiagent Systemscited by 17
  16. 2025When Ethics and Payoffs Diverge: LLM Agents in Morally Charged Social Dilemmascited by 15
  17. 2025Must Read: A Comprehensive Survey of Computational Persuasioncited by 13
  18. 2025The Staircase of Ethics: Probing LLM Value Priorities through Multi-Step Induction to Complex Moral Dilemmascited by 13
  19. 2025Exploring Persona-dependent LLM Alignment for the Moral Machine Experimentcited by 9
  20. 2025Town Hall Debate Prompting: Enhancing Logical Reasoning in LLMs through Multi-Persona Interactioncited by 5
  21. 2020Artificial Artificial Intelligence: Measuring Influence of AI 'Assessments' on Moral Decision-Makingcited by 4
  22. 2024The Future of Cognitive Strategy-enhanced Persuasive Dialogue Agents: New Perspectives and Trendscited by 4
  23. 2024Ethos and Pathos in Online Group Discussions: Corpora for Polarisation Issues in Social Mediacited by 3
  24. 2025Evaluating Chinese Large Language Models: The Influence of Persona Assignment on Stereotypes and Safeguardscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 6; 2026: 13.

19 papers.

Sort:

By area:

  1. 2025Accumulating Context Changes the Beliefs of Language Modelscited by 28
  2. 2025When Identity Skews Debate: Anonymization for Bias-Reduced Multi-Agent Reasoningcited by 21
  3. 2026Colosseum: Auditing Collusion in Cooperative Multi-Agent Systemscited by 18
  4. 2025Humanizing Machines: Rethinking LLM Anthropomorphism Through a Multi-Level Framework of Designcited by 11
  5. 2026The Chameleon's Limit: Investigating Persona Collapse and Homogenization in Large Language Modelscited by 8
  6. 2026Personalization Increases Affective Alignment but Has Role-Dependent Effects on Epistemic Independence in LLMscited by 5
  7. 2025Interaction Protocol Shapes Moral Judgment in Multi-Agent Debatecited by 3
  8. 2025Love First, Know Later: Persona-Based Romantic Compatibility Through LLM Text World Enginescited by 3
  9. 2026Culturally Grounded Personas in Large Language Models: Characterization and Alignment with Socio-Psychological Value Frameworkscited by 3
  10. 2026Evaluating Cooperation in LLM Social Groups through Elected Leadershipcited by 3
  11. 2025Large language models show fragile cognitive reasoning about human emotionscited by 2
  12. 2026Sentipolis: Emotion-Aware Agents for Social Simulationscited by 2
7 more
  1. 2026Re-Centering Humans in LLM Personalizationcited by 1
  2. 2026Every Act Has Its Price: Compressed Moral Composition in Frontier LLMscited by 1
  3. 2026PersonaTeaming: Supporting Persona-Driven Red-Teaming for Generative AIcited by 0
  4. 2026LLM Wardens: Mitigating Adversarial Persuasion with Third-Party Conversational Oversightcited by 0
  5. 2026Staying with the Uncertainty: Uncertainty-Scaffolding Strategies for Artificial Moral Advisors in LLM-to-LLM Simulated Conversationscited by 0
  6. 2026DLawBench: Evaluating LLMs Through Multi-Turn Legal Consultationcited by 0
  7. 2026Readable, Faithful, Used: Three Dissociable Properties of Demographic Identity in a Language Modelcited by 0