# Multiple LLM Agents Debate for Equitable Cultural Alignment

arXiv: https://arxiv.org/abs/2505.24671 · HTML: https://mlsanity.com/paper/2505.24671/

## 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.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 30 of 40)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [Yi: Open Foundation Models by 01.AI](https://mlsanity.com/paper/2403.04652/) (2024)
- [OLMo: Accelerating the Science of Language Models](https://mlsanity.com/paper/2402.00838/) (2024)
- [AI safety via debate](https://mlsanity.com/paper/1805.00899/) (2018)
- [Debating with More Persuasive LLMs Leads to More Truthful Answers](https://mlsanity.com/paper/2402.06782/) (2024)
- [Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies](https://mlsanity.com/paper/2308.03188/) (2023)
- [Evaluating the Moral Beliefs Encoded in LLMs](https://mlsanity.com/paper/2307.14324/) (2023)
- [Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Study](https://mlsanity.com/paper/2303.17466/) (2023)
- [Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration](https://mlsanity.com/paper/2402.00367/) (2024)
- [Probing Pre-Trained Language Models for Cross-Cultural Differences in Values](https://mlsanity.com/paper/2203.13722/) (2022)
- [Investigating Cultural Alignment of Large Language Models](https://mlsanity.com/paper/2402.13231/) (2024)
- [Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences](https://mlsanity.com/paper/2012.15738/) (2020)
- [Aya 23: Open Weight Releases to Further Multilingual Progress](https://mlsanity.com/paper/2405.15032/) (2024)
- [Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration](https://mlsanity.com/paper/2406.15951/) (2024)
- [Cultural Alignment in Large Language Models: An Explanatory Analysis Based on Hofstede's Cultural Dimensions](https://mlsanity.com/paper/2309.12342/) (2023)
- [On scalable oversight with weak LLMs judging strong LLMs](https://mlsanity.com/paper/2407.04622/) (2024)
- [CultureBank: An Online Community-Driven Knowledge Base Towards Culturally Aware Language Technologies](https://mlsanity.com/paper/2404.15238/) (2024)
- [AceGPT, Localizing Large Language Models in Arabic](https://mlsanity.com/paper/2309.12053/) (2023)
- [CULTURE-GEN: Revealing Global Cultural Perception in Language Models through Natural Language Prompting](https://mlsanity.com/paper/2404.10199/) (2024)
- [How Well Do LLMs Represent Values Across Cultures? Empirical Analysis of LLM Responses Based on Hofstede Cultural Dimensions](https://mlsanity.com/paper/2406.14805/) (2024)
- [Understanding the Capabilities and Limitations of Large Language Models for Cultural Commonsense](https://mlsanity.com/paper/2405.04655/) (2024)

## Built on by (most cited first, 21 of 21)

- [Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectives](https://mlsanity.com/paper/2506.09656/) (2025)
- [Building Benchmarks from the Ground Up: Community-Centered Evaluation of LLMs in Healthcare Chatbot Settings](https://mlsanity.com/paper/2509.24506/) (2025)
- [Toward Culturally Aligned LLMs through Ontology-Guided Multi-Agent Reasoning](https://mlsanity.com/paper/2601.21700/) (2026)
- [Multi-Agent Debate Strategies: Survey, Taxonomy, and Challenges](https://mlsanity.com/paper/2607.26212/) (2026)
- [Emergence of Biased Consensus in Multi-Agent LLM Debates](https://mlsanity.com/paper/2608.02827/) (2026)
- [Social Dynamics as Critical Vulnerabilities that Undermine Objective Decision-Making in LLM Collectives](https://mlsanity.com/paper/2604.06091/) (2026)
- [Cross-Lingual Stability and Bias in Instruction-Tuned Language Models for Humanitarian NLP](https://mlsanity.com/paper/2510.22823/) (2025)
- [Mitigating Cultural Bias in LLMs via Multi-Agent Cultural Debate](https://mlsanity.com/paper/2601.12091/) (2026)
- [The Deliberative Illusion: Diagnosing Factual Attrition and Stance Homogenization in Multi-Agent LLM Deliberation](https://mlsanity.com/paper/2606.03032/) (2026)
- [ReCCur: A Recursive Corner-Case Curation Framework for Robust Vision-Language Understanding in Open and Edge Scenarios](https://mlsanity.com/paper/2601.03011/) (2026)
- [Pragmatics Meets Culture: Culturally-adapted Artwork Description Generation and Evaluation](https://mlsanity.com/paper/2604.02557/) (2026)
- [Cross-Cultural Simulation of Citizen Emotional Responses to Bureaucratic Red Tape Using LLM Agents](https://mlsanity.com/paper/2604.12545/) (2026)
- [SoCRATES: Towards Reliable Automated Evaluation of Proactive LLM Mediation across Domains and Socio-cognitive Variations](https://mlsanity.com/paper/2606.05563/) (2026)
- [DECIS: Dual-Evidence Corrective Verification for Interpretable Strabismus Diagnostic Decision-Making](https://mlsanity.com/paper/2606.09249/) (2026)
- [AutoJourn: Multi-Perspective Summarisation, Bias Detection and Bias Neutralisation for LLM-Generated News in Automated Journalism](https://mlsanity.com/paper/2607.18983/) (2026)
- [Do LLM Debates Repeat Arguments Differently Across Languages?](https://mlsanity.com/paper/2607.23442/) (2026)
- [A Theory of Post-hoc Debate Judgement](https://mlsanity.com/paper/2608.19002/) (2026)
- [ExpertIVS: Sociological Expert Driven Individual Value Simulation in Large Language Models](https://mlsanity.com/paper/2608.20355/) (2026)
- [Aligned but Flattened: Analyzing the Trade-off between Cultural Alignment and Diversity in LLMs](https://mlsanity.com/paper/2609.00565/) (2026)
- [CultureMINE: Datasets and Methods for Improving the Cultural Capabilities of NLP Systems](https://mlsanity.com/paper/2609.22494/) (2026)
- [Right Answers, Wrong States: Hidden Information Failures in Multi-Agent Collaboration](https://mlsanity.com/paper/2610.01244/) (2026)

## 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).