# Language Model Alignment in Multilingual Trolley Problems

arXiv: https://arxiv.org/abs/2407.02273 · HTML: https://mlsanity.com/paper/2407.02273/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 56 of its 85 references that are in the map.
- First posted on arXiv 2 Jul 2024.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)

## Builds on (most cited first, 30 of 56)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [XNLI: Evaluating Cross-lingual Sentence Representations](https://mlsanity.com/paper/1809.05053/) (2018)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Aligning AI With Shared Human Values](https://mlsanity.com/paper/2008.02275/) (2020)
- [Yi: Open Foundation Models by 01.AI](https://mlsanity.com/paper/2403.04652/) (2024)
- [On the Cross-lingual Transferability of Monolingual Representations](https://mlsanity.com/paper/1910.11856/) (2019)
- [The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation](https://mlsanity.com/paper/2106.03193/) (2021)
- [Towards Measuring the Representation of Subjective Global Opinions in Language Models](https://mlsanity.com/paper/2306.16388/) (2023)
- [Are aligned neural networks adversarially aligned?](https://mlsanity.com/paper/2306.15447/) (2023)
- [MEGA: Multilingual Evaluation of Generative AI](https://mlsanity.com/paper/2303.12528/) (2023)
- [Unsolved Problems in ML Safety](https://mlsanity.com/paper/2109.13916/) (2021)
- [Social Chemistry 101: Learning to Reason about Social and Moral Norms](https://mlsanity.com/paper/2011.00620/) (2020)
- [Evaluating the Moral Beliefs Encoded in LLMs](https://mlsanity.com/paper/2307.14324/) (2023)
- [Foundational Challenges in Assuring Alignment and Safety of Large Language Models](https://mlsanity.com/paper/2404.09932/) (2024)
- [A Roadmap to Pluralistic Alignment](https://mlsanity.com/paper/2402.05070/) (2024)
- [Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do](https://mlsanity.com/paper/2103.11790/) (2021)
- [Is ChatGPT A Good Translator? Yes With GPT-4 As The Engine](https://mlsanity.com/paper/2301.08745/) (2023)

## Built on by (most cited first, 30 of 46)

- [Cultivating Pluralism In Algorithmic Monoculture: The Community Alignment Dataset](https://mlsanity.com/paper/2507.09650/) (2025)
- [Multiple LLM Agents Debate for Equitable Cultural Alignment](https://mlsanity.com/paper/2505.24671/) (2025)
- [Synthetic Socratic Debates: Examining Persona Effects on Moral Decision and Persuasion Dynamics](https://mlsanity.com/paper/2506.12657/) (2025)
- [Stress-Testing Model Specs Reveals Character Differences among Language Models](https://mlsanity.com/paper/2510.07686/) (2025)
- [The Lock-in Hypothesis: Stagnation by Algorithm](https://mlsanity.com/paper/2506.06166/) (2025)
- [Discerning What Matters: A Multi-Dimensional Assessment of Moral Competence in LLMs](https://mlsanity.com/paper/2506.13082/) (2025)
- [Exploring Persona-dependent LLM Alignment for the Moral Machine Experiment](https://mlsanity.com/paper/2504.10886/) (2025)
- [LIVS: A Pluralistic Alignment Dataset for Inclusive Public Spaces](https://mlsanity.com/paper/2503.01894/) (2025)
- [ManagerBench: Evaluating the Safety-Pragmatism Trade-off in Autonomous LLMs](https://mlsanity.com/paper/2510.00857/) (2025)
- [Agent-to-Agent Theory of Mind: Testing Interlocutor Awareness among Large Language Models](https://mlsanity.com/paper/2506.22957/) (2025)
- [Aligning Large Language Model Agents with Rational and Moral Preferences: A Supervised Fine-Tuning Approach](https://mlsanity.com/paper/2507.20796/) (2025)
- [Language Specific Knowledge: Do Models Know Better in X than in English?](https://mlsanity.com/paper/2505.14990/) (2025)
- [Bias Beyond Borders: Political Ideology Evaluation and Steering in Multilingual LLMs](https://mlsanity.com/paper/2601.23001/) (2026)
- [Multilingual LLMs Struggle to Link Orthography and Semantics in Bilingual Word Processing](https://mlsanity.com/paper/2501.09127/) (2025)
- [The Right to AI](https://mlsanity.com/paper/2501.17899/) (2025)
- ["Pull or Not to Pull?'': Investigating Moral Biases in Leading Large Language Models Across Ethical Dilemmas](https://mlsanity.com/paper/2508.07284/) (2025)
- [EVALUESTEER: Measuring Reward Model Steerability Towards Values and Preferences](https://mlsanity.com/paper/2510.06370/) (2025)
- [Evaluating Cooperation in LLM Social Groups through Elected Leadership](https://mlsanity.com/paper/2604.11721/) (2026)
- [Dropouts in Confidence: Moral Uncertainty in Human-LLM Alignment](https://mlsanity.com/paper/2511.13290/) (2025)
- [MOSAIC: Unveiling the Moral, Social and Individual Dimensions of Large Language Models](https://mlsanity.com/paper/2603.00048/) (2026)
- [Language Shapes Mental Health Evaluations in Large Language Models](https://mlsanity.com/paper/2603.06910/) (2026)
- [Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability](https://mlsanity.com/paper/2605.03217/) (2026)
- [Incoherent Values? Probing LLM Preferences Through Parametric Variation](https://mlsanity.com/paper/2606.21102/) (2026)
- [Reward Model Perspectives: Whose Opinions Do Reward Models Reward?](https://mlsanity.com/paper/2510.06391/) (2025)
- [Explainable Ethical Assessment on Human Behaviors by Generating Conflicting Social Norms](https://mlsanity.com/paper/2512.15793/) (2025)
- [A Rising Tide Lifts All Boats: MTQE Rewards for Idioms Improve General Translation Quality](https://mlsanity.com/paper/2601.06307/) (2026)
- [When Do Language Models Endorse Limitations on Human Rights Principles?](https://mlsanity.com/paper/2603.04217/) (2026)
- [Are Dilemmas and Conflicts in LLM Alignment Solvable? A View from Priority Graph](https://mlsanity.com/paper/2603.15527/) (2026)
- [GAIN: A Benchmark for Goal-Aligned Decision-Making of Large Language Models under Imperfect Norms](https://mlsanity.com/paper/2603.18469/) (2026)
- [Conflicts Make Large Reasoning Models Vulnerable to Attacks](https://mlsanity.com/paper/2604.09750/) (2026)

## Abstract (arXiv)

We evaluate the moral alignment of LLMs with human preferences in multilingual trolley problems. Building on the Moral Machine experiment, which captures over 40 million human judgments across 200+ countries, we develop a cross-lingual corpus of moral dilemma vignettes in over 100 languages called MultiTP. This dataset enables the assessment of LLMs' decision-making processes in diverse linguistic contexts. Our analysis explores the alignment of 19 different LLMs with human judgments, capturing preferences across six moral dimensions: species, gender, fitness, status, age, and the number of lives involved. By correlating these preferences with the demographic distribution of language speakers and examining the consistency of LLM responses to various prompt paraphrasings, our findings provide insights into cross-lingual and ethical biases of LLMs and their intersection. We discover significant variance in alignment across languages, challenging the assumption of uniform moral reasoning in AI systems and highlighting the importance of incorporating diverse perspectives in AI ethics. The results underscore the need for further research on the integration of multilingual dimensions in responsible AI research to ensure fair and equitable AI interactions worldwide. Our code and data are at https://github.com/causalNLP/moralmachine