Exploring Cultural Variations in Moral Judgments with Large Language Models

2025/06/14 by Hadi Mohammadi, Mohammadi, Hadi, Ayoub Bagheri +3 · 1 citation
Social Sciences · #Computational and Text Analysis Methods

paper · pdf · doi:10.48550/arxiv.2506.12433

Abstract

Code, model outputs, and analysis for evaluating 26 large language models against the World Values Survey (55 countries) and the PEW Global Attitudes Survey (39 countries) across 19 ethical topics, documenting a persistent W.E.I.R.D. (Western, Educated, Industrialised, Rich, Democratic) bias. Archived snapshot for the v1.0-thesis release accompanying the doctoral thesis Let Me Explain! Explainable NLP for Understanding Large Language Models (Utrecht University, 2026).

Citations

• Do Large Language Models Understand Morality Across Cultures?
• Assessing the Reliability of LLMs Annotations in the Context of Demographic Bias and Model Explanation
• Explainability-Based Token Replacement on LLM-Generated Text
• The Greatest Good Benchmark: Measuring LLMs' Alignment with Utilitarian Moral Dilemmas
• Explainability in Practice: A Survey of Explainable NLP Across Various Domains
• Large Language Models as Mirrors of Societal Moral Standards
• LLMs as mirrors of societal moral standards: reflection of cultural divergence and agreement across ethical topics
• Evaluating Moral Beliefs across LLMs through a Pluralistic Framework
• Intrinsic Self-correction for Enhanced Morality: An Analysis of Internal Mechanisms and the Superficial Hypothesis
• How Well Do LLMs Represent Values Across Cultures? Empirical Analysis of LLM Responses Based on Hofstede Cultural Dimensions
• Ethical Reasoning and Moral Value Alignment of LLMs Depend on the Language we Prompt them in
• WorldValuesBench: A Large-Scale Benchmark Dataset for Multi-Cultural Value Awareness of Language Models
• Chinese Tiny LLM: Pretraining a Chinese-Centric Large Language Model
• Towards Measuring and Modeling "Culture" in LLMs: A Survey
• Assessing LLMs for Moral Value Pluralism
• The Falcon Series of Open Language Models
• Cultural bias and cultural alignment of large language models
• Moral Foundations of Large Language Models
• Qwen Technical Report
• Are Multilingual LLMs Culturally-Diverse Reasoners? An Investigation into Multicultural Proverbs and Sayings
• Evaluating the Moral Beliefs Encoded in LLMs
• Knowledge of cultural moral norms in large language models
• Diversity and Inclusion in Artificial Intelligence
• Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Study
• BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
• OPT: Open Pre-trained Transformer Language Models
• GPT-NeoX-20B: An Open-Source Autoregressive Language Model
• Probing Pre-Trained Language Models for Cross-Cultural Differences in Values
• Do Multilingual Language Models Capture Differing Moral Norms?
• The Ghost in the Machine has an American accent: value conflict in GPT-3
• A Survey on Gender Bias in Natural Language Processing
• On the Dangers of Stochastic Parrots
• Language Models are Few-Shot Learners
• StereoSet: Measuring stereotypical bias in pretrained language models
• Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
• Attention Is All You Need
• The emotional dog and its rational tail: A social intuitionist approach to moral judgment.

Cited by

• Do Large Language Models Understand Morality Across Cultures?

Related

• Do Large Language Models Understand Morality Across Cultures?
• LLMs as mirrors of societal moral standards: reflection of cultural divergence and agreement across ethical topics
• Large Language Models as Mirrors of Societal Moral Standards
• Whose Morality Do They Speak? Unraveling Cultural Bias in Multilingual Language Models
• Knowledge of cultural moral norms in large language models