mlsanityData to 7 Oct 2026

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

arXiv 2412.18863 ↗First posted 25 Dec 2024cs.CL cs.AIcited by 17

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

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.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 25 of its 63 references that are in the map. First posted on arXiv 25 Dec 2024.

Builds on

25 of 63 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting11 May
  2. 2023LLaMA: Open and Efficient Foundation Language Models27 Feb
  3. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity8 Feb

Other references · 22

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  4. 2023A Survey of Large Language Modelscited by 2,537
  5. 2022GLM-130B: An Open Bilingual Pre-trained Modelcited by 837
  6. 2023Towards Measuring the Representation of Subjective Global Opinions in Language Modelscited by 424
  7. 2020Social Chemistry 101: Learning to Reason about Social and Moral Normscited by 253
  8. 2023Multilingual Machine Translation with Large Language Models: Empirical Results and Analysiscited by 156
  9. 2023Having Beer after Prayer? Measuring Cultural Bias in Large Language Modelscited by 153
  10. 2022Probing Pre-Trained Language Models for Cross-Cultural Differences in Valuescited by 147
  11. 2021Can Machines Learn Morality? The Delphi Experimentcited by 140
  12. 2023Moral Foundations of Large Language Modelscited by 84
10 more
  1. 2024MoralBench: Moral Evaluation of LLMscited by 50
  2. 2023Improving Diversity of Demographic Representation in Large Language Models via Collective-Critiques and Self-Votingcited by 46
  3. 2023Democratizing LLMs for Low-Resource Languages by Leveraging their English Dominant Abilities with Linguistically-Diverse Promptscited by 45
  4. 2022Speaking Multiple Languages Affects the Moral Bias of Language Modelscited by 34
  5. 2023Assessing LLMs for Moral Value Pluralismcited by 34
  6. 2022Does Moral Code Have a Moral Code? Probing Delphi's Moral Philosophycited by 31
  7. 2024Evaluating the Elementary Multilingual Capabilities of Large Language Models with MultiQcited by 27
  8. 2024Exploring and steering the moral compass of Large Language Modelscited by 15
  9. 2024Decoding Multilingual Moral Preferences: Unveiling LLM's Biases Through the Moral Machine Experimentcited by 11
  10. 2024SaGE: Evaluating Moral Consistency in Large Language Modelscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 10; 2026: 7.

17 papers.

Sort:

By area:

  1. 2025Made-in China, Thinking in America:U.S. Values Persist in Chinese LLMscited by 5
  2. 2025One Model, Many Morals: Uncovering Cross-Linguistic Misalignments in Computational Moral Reasoningcited by 4
  3. 2025Moral Susceptibility and Robustness under Persona Role-Play in Large Language Modelscited by 4
  4. 2026Tracing Moral Foundations in Large Language Modelscited by 4
  5. 2026On the Credibility of Evaluating LLMs using Survey Questionscited by 3
  6. 2025Choosing a Model, Shaping a Future: Comparing LLM Perspectives on Sustainability and its Relationship with AIcited by 2
  7. 2025Evaluating Modern Large Language Models on Low-Resource and Morphologically Rich Languages:A Cross-Lingual Benchmark Across Cantonese, Japanese, and Turkishcited by 2
  8. 2025What if I ask in textitalia lingua? Measuring Functional Similarity Across Languagescited by 1
  9. 2026Language Models Entangle Language and Culturecited by 1
  10. 2026Investigating the Influence of Language on Sycophantic Behavior of Multilingual LLMscited by 1
  11. 2026Moral Semantics Survive Machine Translation: Cross-Lingual Evidence from Moral Foundations Corporacited by 1
  12. 2025ALIGN: Word Association Learning for Cultural Alignment in Large Language Modelscited by 0
5 more
  1. 2025Demographic Biases and Gaps in the Perception of Sexism in Large Language Modelscited by 0
  2. 2025The Curious Case of Curiosity across Human Cultures and LLMscited by 0
  3. 2025A Detailed Study on LLM Biases Concerning Corporate Social Responsibility and Green Supply Chainscited by 0
  4. 2026Whose Norms? Disentangling Cultural and Personal Alignment in Large Language Modelscited by 0
  5. 2026Steering LLMs Responses Towards Moral Foundations on the Norwegian MFQ-30cited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Ethical Reasoning and Moral Value Alignment of LLMs Depend on the Language we Prompt them in
  2. 2025Cultural Bias in Large Language Models: Evaluating AI Agents through Moral Questionnaires
  3. 2024Do Moral Judgment and Reasoning Capability of LLMs Change with Language? A Study using the Multilingual Defining Issues Test
  4. 2025From Stability to Inconsistency: A Study of Moral Preferences in LLMs
  5. 2024Language Model Alignment in Multilingual Trolley Problems
  6. 2026MET: Theory-Grounded and Culture-Aware Multilingual Moral Reasoning
  7. 2025Cultural Value Alignment in Large Language Models: A Prompt-based Analysis of Schwartz Values in Gemini, ChatGPT, and DeepSeek
  8. 2025Moral Reasoning Across Languages: The Critical Role of Low-Resource Languages in LLMs