# Mitigating Cultural Bias in LLMs via Multi-Agent Cultural Debate

arXiv: https://arxiv.org/abs/2601.12091 · HTML: https://mlsanity.com/paper/2601.12091/

## Key facts

- Cited by 1 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 20 of its 34 references that are in the map.
- First posted on arXiv 17 Jan 2026.

## 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, 20 of 20)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus](https://mlsanity.com/paper/2104.08758/) (2021)
- [Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Study](https://mlsanity.com/paper/2303.17466/) (2023)
- [Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation](https://mlsanity.com/paper/2412.03304/) (2024)
- [BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languages](https://mlsanity.com/paper/2406.09948/) (2024)
- [MaxMin-RLHF: Alignment with Diverse Human Preferences](https://mlsanity.com/paper/2402.08925/) (2024)
- [Cultural Alignment in Large Language Models: An Explanatory Analysis Based on Hofstede's Cultural Dimensions](https://mlsanity.com/paper/2309.12342/) (2023)
- [Survey of Cultural Awareness in Language Models: Text and Beyond](https://mlsanity.com/paper/2411.00860/) (2024)
- [CultureBank: An Online Community-Driven Knowledge Base Towards Culturally Aware Language Technologies](https://mlsanity.com/paper/2404.15238/) (2024)
- [Group Robust Preference Optimization in Reward-free RLHF](https://mlsanity.com/paper/2405.20304/) (2024)
- [Understanding and Mitigating Language Confusion in LLMs](https://mlsanity.com/paper/2406.20052/) (2024)
- [CULTURE-GEN: Revealing Global Cultural Perception in Language Models through Natural Language Prompting](https://mlsanity.com/paper/2404.10199/) (2024)
- [Evaluating Cultural and Social Awareness of LLM Web Agents](https://mlsanity.com/paper/2410.23252/) (2024)
- [An Evaluation of Cultural Value Alignment in LLM](https://mlsanity.com/paper/2504.08863/) (2025)
- [On The Origin of Cultural Biases in Language Models: From Pre-training Data to Linguistic Phenomena](https://mlsanity.com/paper/2501.04662/) (2025)
- [Multiple LLM Agents Debate for Equitable Cultural Alignment](https://mlsanity.com/paper/2505.24671/) (2025)
- [Bias in the Mirror: Are LLMs opinions robust to their own adversarial attacks ?](https://mlsanity.com/paper/2410.13517/) (2024)
- [Cultural Bias in Large Language Models: Evaluating AI Agents through Moral Questionnaires](https://mlsanity.com/paper/2507.10073/) (2025)

## Built on by (most cited first, 1 of 1)

- [Toward an AI-Powered Computational Testbed for Workforce Policy](https://mlsanity.com/paper/2605.19064/) (2026)

## Abstract (arXiv)

Large language models (LLMs) exhibit systematic Western-centric bias, yet whether prompting in non-Western languages (e.g., Chinese) can mitigate this remains understudied. Answering this question requires rigorous evaluation and effective mitigation, but existing approaches fall short on both fronts: evaluation methods force outputs into predefined cultural categories without a neutral option, while mitigation relies on expensive multi-cultural corpora or agent frameworks that use functional roles (e.g., Planner--Critique) lacking explicit cultural representation. To address these gaps, we introduce CEBiasBench, a Chinese--English bilingual benchmark, and Multi-Agent Vote (MAV), which enables explicit ``no bias'' judgments. Using this framework, we find that Chinese prompting merely shifts bias toward East Asian perspectives rather than eliminating it. To mitigate such persistent bias, we propose Multi-Agent Cultural Debate (MACD), a training-free framework that assigns agents distinct cultural personas and orchestrates deliberation via a "Seeking Common Ground while Reserving Differences" strategy. Experiments demonstrate that MACD achieves 57.6% average No Bias Rate evaluated by LLM-as-judge and 86.0% evaluated by MAV (vs. 47.6% and 69.0% baseline using GPT-4o as backbone) on CEBiasBench and generalizes to the Arabic CAMeL benchmark, confirming that explicit cultural representation in agent frameworks is essential for cross-cultural fairness.