A Game-Theoretic Negotiation Framework for Cross-Cultural Consensus in LLMs

TL;DR

This paper introduces a game-theoretic negotiation framework using policy-space response oracles to promote fair cross-cultural consensus in large language models, reducing WEIRD bias and enhancing inclusivity.

Contribution

It presents a novel game-theoretic approach with quantitative metrics for evaluating cross-cultural consensus in LLMs, addressing cultural bias issues.

Findings

Higher quality consensus achieved compared to baselines

More balanced and fair cultural compromise

Mitigates WEIRD bias in language models

Abstract

The increasing prevalence of large language models (LLMs) is influencing global value systems. However, these models frequently exhibit a pronounced WEIRD (Western, Educated, Industrialized, Rich, Democratic) cultural bias due to lack of attention to minority values. This monocultural perspective may reinforce dominant values and marginalize diverse cultural viewpoints, posing challenges for the development of equitable and inclusive AI systems. In this work, we introduce a systematic framework designed to boost fair and robust cross-cultural consensus among LLMs. We model consensus as a Nash Equilibrium and employ a game-theoretic negotiation method based on Policy-Space Response Oracles (PSRO) to simulate an organized cross-cultural negotiation process. To evaluate this approach, we construct regional cultural agents using data transformed from the World Values Survey (WVS). Beyond the conventional model-level evaluation method, We further propose two quantitative metrics, Perplexity-based Acceptence and Values Self-Consistency, to assess consensus outcomes. Experimental results indicate that our approach generates consensus of higher quality while ensuring more balanced compromise compared to baselines. Overall, it mitigates WEIRD bias by guiding agents toward convergence through fair and gradual negotiation steps.