Whose Morality Do They Speak? Unraveling Cultural Bias in Multilingual Language Models

TL;DR

This paper examines whether multilingual large language models reflect culturally specific moral values or impose dominant norms, revealing significant variability and biases influenced by training data across different languages and cultures.

Contribution

It provides a comprehensive analysis of moral reasoning in multilingual LLMs using the Moral Foundations Questionnaire across eight languages, highlighting cultural biases and variability.

Findings

Significant cultural and linguistic variability in moral judgments.

Some models adapt to diverse moral contexts, others show biases.

Training data influences models' moral biases.

Abstract

Large language models (LLMs) have become integral tools in diverse domains, yet their moral reasoning capabilities across cultural and linguistic contexts remain underexplored. This study investigates whether multilingual LLMs, such as GPT-3.5-Turbo, GPT-4o-mini, Llama 3.1, and MistralNeMo, reflect culturally specific moral values or impose dominant moral norms, particularly those rooted in English. Using the updated Moral Foundations Questionnaire (MFQ-2) in eight languages, Arabic, Farsi, English, Spanish, Japanese, Chinese, French, and Russian, the study analyzes the models' adherence to six core moral foundations: care, equality, proportionality, loyalty, authority, and purity. The results reveal significant cultural and linguistic variability, challenging the assumption of universal moral consistency in LLMs. Although some models demonstrate adaptability to diverse contexts, others exhibit biases influenced by the composition of the training data. These findings underscore the need for culturally inclusive model development to improve fairness and trust in multilingual AI systems.