# Decoding Multilingual Moral Preferences: Unveiling LLM's Biases Through the Moral Machine Experiment

arXiv: https://arxiv.org/abs/2407.15184 · HTML: https://mlsanity.com/paper/2407.15184/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 26 references that are in the map.
- First posted on arXiv 21 Jul 2024.

## Builds on (most cited first, 7 of 7)

- [Evaluating the Moral Beliefs Encoded in LLMs](https://mlsanity.com/paper/2307.14324/) (2023)
- [Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions?](https://mlsanity.com/paper/2106.01465/) (2021)
- [Speaking Multiple Languages Affects the Moral Bias of Language Models](https://mlsanity.com/paper/2211.07733/) (2022)
- [Assessing LLMs for Moral Value Pluralism](https://mlsanity.com/paper/2312.10075/) (2023)
- [Evaluating the Elementary Multilingual Capabilities of Large Language Models with MultiQ](https://mlsanity.com/paper/2403.03814/) (2024)
- [A Word on Machine Ethics: A Response to Jiang et al. (2021)](https://mlsanity.com/paper/2111.04158/) (2021)
- [BERT has a Moral Compass: Improvements of ethical and moral values of machines](https://mlsanity.com/paper/1912.05238/) (2019)

## Built on by (most cited first, 11 of 11)

- [Whose Morality Do They Speak? Unraveling Cultural Bias in Multilingual Language Models](https://mlsanity.com/paper/2412.18863/) (2024)
- [Large-scale moral machine experiment on large language models](https://mlsanity.com/paper/2411.06790/) (2024)
- [Should LLMs be WEIRD? Exploring WEIRDness and Human Rights in Large Language Models](https://mlsanity.com/paper/2508.19269/) (2025)
- [One world, one opinion? The superstar effect in LLM responses](https://mlsanity.com/paper/2412.10281/) (2024)
- [C-VARC: A Large-Scale Chinese Value Rule Corpus for Value Alignment of Large Language Models](https://mlsanity.com/paper/2506.01495/) (2025)
- [On the Credibility of Evaluating LLMs using Survey Questions](https://mlsanity.com/paper/2602.04033/) (2026)
- [What if I ask in textitalia lingua? Measuring Functional Similarity Across Languages](https://mlsanity.com/paper/2509.04032/) (2025)
- [Implicit Values Embedded in How Humans and LLMs Complete Subjective Everyday Tasks](https://mlsanity.com/paper/2510.03384/) (2025)
- [OpenEthics: A Comprehensive Ethical Evaluation of Open-Source Generative Large Language Models](https://mlsanity.com/paper/2505.16036/) (2025)
- [Which Institutional Frameworks Do Chatbots Assume? Auditing Jurisdictional Defaults in Multilingual LLMs](https://mlsanity.com/paper/2606.00333/) (2026)
- [Greener Than Humans? Environmental Attitudes in Large Language Models](https://mlsanity.com/paper/2606.02741/) (2026)

## Abstract (arXiv)

Large language models (LLMs) increasingly find their way into the most diverse areas of our everyday lives. They indirectly influence people's decisions or opinions through their daily use. Therefore, understanding how and which moral judgements these LLMs make is crucial. However, morality is not universal and depends on the cultural background. This raises the question of whether these cultural preferences are also reflected in LLMs when prompted in different languages or whether moral decision-making is consistent across different languages. So far, most research has focused on investigating the inherent values of LLMs in English. While a few works conduct multilingual analyses of moral bias in LLMs in a multilingual setting, these analyses do not go beyond atomic actions. To the best of our knowledge, a multilingual analysis of moral bias in dilemmas has not yet been conducted. To address this, our paper builds on the moral machine experiment (MME) to investigate the moral preferences of five LLMs, Falcon, Gemini, Llama, GPT, and MPT, in a multilingual setting and compares them with the preferences collected from humans belonging to different cultures. To accomplish this, we generate 6500 scenarios of the MME and prompt the models in ten languages on which action to take. Our analysis reveals that all LLMs inhibit different moral biases to some degree and that they not only differ from the human preferences but also across multiple languages within the models themselves. Moreover, we find that almost all models, particularly Llama 3, divert greatly from human values and, for instance, prefer saving fewer people over saving more.