mlsanityData to 14 Oct 2026

Multiple LLM Agents Debate for Equitable Cultural Alignment

arXiv 2505.24671 ↗First posted 30 May 2025cs.CL cs.AIcited by 21

On the map: LLM agents and tool use → Social simulation and multi-agent debate

Abstract (arXiv)

Large Language Models (LLMs) need to adapt their predictions to diverse cultural contexts to benefit diverse communities across the world. While previous efforts have focused on single-LLM, single-turn approaches, we propose to exploit the complementary strengths of multiple LLMs to promote cultural adaptability. We introduce a Multi-Agent Debate framework, where two LLM-based agents debate over a cultural scenario and collaboratively reach a final decision. We propose two variants: one where either LLM agents exclusively debate and another where they dynamically choose between self-reflection and debate during their turns. We evaluate these approaches on 7 open-weight LLMs (and 21 LLM combinations) using the NormAd-ETI benchmark for social etiquette norms in 75 countries. Experiments show that debate improves both overall accuracy and cultural group parity over single-LLM baselines. Notably, multi-agent debate enables relatively small LLMs (7-9B) to achieve accuracies comparable to that of a much larger model (27B parameters).

Key facts. Cited by 21 papers in the map (data through 14 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 40 of its 57 references that are in the map. First posted on arXiv 30 May 2025.

Builds on

40 of 57 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate30 May

Other references · 39

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  4. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  5. 2022Language Models (Mostly) Know What They Knowcited by 1,856
  6. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  7. 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 956
  8. 2022Discovering Language Model Behaviors with Model-Written Evaluationscited by 836
  9. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debatecited by 742
  10. 2024Yi: Open Foundation Models by 01.AIcited by 719
  11. 2024OLMo: Accelerating the Science of Language Modelscited by 613
  12. 2018AI safety via debatecited by 400
27 more
  1. 2024Debating with More Persuasive LLMs Leads to More Truthful Answerscited by 266
  2. 2023Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategiescited by 238
  3. 2023Evaluating the Moral Beliefs Encoded in LLMscited by 215
  4. 2023Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Studycited by 206
  5. 2024Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaborationcited by 180
  6. 2022Probing Pre-Trained Language Models for Cross-Cultural Differences in Valuescited by 149
  7. 2024Investigating Cultural Alignment of Large Language Modelscited by 143
  8. 2020Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequencescited by 135
  9. 2024Aya 23: Open Weight Releases to Further Multilingual Progresscited by 123
  10. 2024Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaborationcited by 113
  11. 2023Cultural Alignment in Large Language Models: An Explanatory Analysis Based on Hofstede's Cultural Dimensionscited by 112
  12. 2024On scalable oversight with weak LLMs judging strong LLMscited by 99
  13. 2024CultureBank: An Online Community-Driven Knowledge Base Towards Culturally Aware Language Technologiescited by 98
  14. 2023AceGPT, Localizing Large Language Models in Arabiccited by 75
  15. 2024CULTURE-GEN: Revealing Global Cultural Perception in Language Models through Natural Language Promptingcited by 55
  16. 2024How Well Do LLMs Represent Values Across Cultures? Empirical Analysis of LLM Responses Based on Hofstede Cultural Dimensionscited by 52
  17. 2024Understanding the Capabilities and Limitations of Large Language Models for Cultural Commonsensecited by 51
  18. 2023Improving Diversity of Demographic Representation in Large Language Models via Collective-Critiques and Self-Votingcited by 46
  19. 2024Language Model Alignment in Multilingual Trolley Problemscited by 46
  20. 2021Assessing Multilingual Fairness in Pre-trained Multimodal Representationscited by 35
  21. 2024LLM Augmented LLMs: Expanding Capabilities through Compositioncited by 35
  22. 2024Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statementscited by 34
  23. 2023NormDial: A Comparable Bilingual Synthetic Dialog Dataset for Modeling Social Norm Adherence and Violationcited by 24
  24. 2024EXAONE 3.0 7.8B Instruction Tuned Language Modelcited by 21
  25. 2024Self-Alignment: Improving Alignment of Cultural Values in LLMs via In-Context Learningcited by 19
  26. 2024RENOVI: A Benchmark Towards Remediating Norm Violations in Socio-Cultural Conversationscited by 14
  27. 2024Does Cross-Cultural Alignment Change the Commonsense Morality of Language Models?cited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 18.

21 papers.

Sort:

By area:

  1. 2025Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectivescited by 5
  2. 2025Building Benchmarks from the Ground Up: Community-Centered Evaluation of LLMs in Healthcare Chatbot Settingscited by 5
  3. 2026Toward Culturally Aligned LLMs through Ontology-Guided Multi-Agent Reasoningcited by 3
  4. 2026Multi-Agent Debate Strategies: Survey, Taxonomy, and Challengescited by 3
  5. 2026Emergence of Biased Consensus in Multi-Agent LLM Debatescited by 3
  6. 2026Social Dynamics as Critical Vulnerabilities that Undermine Objective Decision-Making in LLM Collectivescited by 2
  7. 2025Cross-Lingual Stability and Bias in Instruction-Tuned Language Models for Humanitarian NLPcited by 1
  8. 2026Mitigating Cultural Bias in LLMs via Multi-Agent Cultural Debatecited by 1
  9. 2026The Deliberative Illusion: Diagnosing Factual Attrition and Stance Homogenization in Multi-Agent LLM Deliberationcited by 1
  10. 2026ReCCur: A Recursive Corner-Case Curation Framework for Robust Vision-Language Understanding in Open and Edge Scenarioscited by 0
  11. 2026Pragmatics Meets Culture: Culturally-adapted Artwork Description Generation and Evaluationcited by 0
  12. 2026Cross-Cultural Simulation of Citizen Emotional Responses to Bureaucratic Red Tape Using LLM Agentscited by 0
9 more
  1. 2026SoCRATES: Towards Reliable Automated Evaluation of Proactive LLM Mediation across Domains and Socio-cognitive Variationscited by 0
  2. 2026DECIS: Dual-Evidence Corrective Verification for Interpretable Strabismus Diagnostic Decision-Makingcited by 0
  3. 2026AutoJourn: Multi-Perspective Summarisation, Bias Detection and Bias Neutralisation for LLM-Generated News in Automated Journalismcited by 0
  4. 2026Do LLM Debates Repeat Arguments Differently Across Languages?cited by 0
  5. 2026A Theory of Post-hoc Debate Judgementcited by 0
  6. 2026ExpertIVS: Sociological Expert Driven Individual Value Simulation in Large Language Modelscited by 0
  7. 2026Aligned but Flattened: Analyzing the Trade-off between Cultural Alignment and Diversity in LLMscited by 0
  8. 2026CultureMINE: Datasets and Methods for Improving the Cultural Capabilities of NLP Systemscited by 0
  9. 2026Right Answers, Wrong States: Hidden Information Failures in Multi-Agent Collaborationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs
  2. 2025Beyond Single Models: Enhancing LLM Detection of Ambiguity in Requests through Debate
  3. 2026Understanding Cultural Alignment in Multilingual LLMs via Natural Debate Statements ↗
  4. 2026Collective Opinion Dynamics in Structured LLM Populations
  5. 2026From Diagnosis to Redesign: Using Quantitative Ethnography to Improve Multi-Agent LLM Reasoning
  6. 2025Debate Only When Necessary: Adaptive Multiagent Collaboration for Efficient LLM Reasoning
  7. 2025Beyond Static Responses: Multi-Agent LLM Systems as a New Paradigm for Social Science Research
  8. 2025Randomness, Not Representation: The Unreliability of Evaluating Cultural Alignment in LLMs