# Ethical Reasoning and Moral Value Alignment of LLMs Depend on the Language we Prompt them in

arXiv: https://arxiv.org/abs/2404.18460 · HTML: https://mlsanity.com/paper/2404.18460/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 16 of its 50 references that are in the map.
- First posted on arXiv 29 Apr 2024.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 16 of 16)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Aligning AI With Shared Human Values](https://mlsanity.com/paper/2008.02275/) (2020)
- [How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation](https://mlsanity.com/paper/2302.09210/) (2023)
- [MEGA: Multilingual Evaluation of Generative AI](https://mlsanity.com/paper/2303.12528/) (2023)
- [Is ChatGPT A Good Translator? Yes With GPT-4 As The Engine](https://mlsanity.com/paper/2301.08745/) (2023)
- [Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting](https://mlsanity.com/paper/2305.07004/) (2023)
- [Re-imagining Algorithmic Fairness in India and Beyond](https://mlsanity.com/paper/2101.09995/) (2021)
- [SeaEval for Multilingual Foundation Models: From Cross-Lingual Alignment to Cultural Reasoning](https://mlsanity.com/paper/2309.04766/) (2023)
- [Ethical Reasoning over Moral Alignment: A Case and Framework for In-Context Ethical Policies in LLMs](https://mlsanity.com/paper/2310.07251/) (2023)
- [Re-contextualizing Fairness in NLP: The Case of India](https://mlsanity.com/paper/2209.12226/) (2022)
- [Large Language Models as Superpositions of Cultural Perspectives](https://mlsanity.com/paper/2307.07870/) (2023)
- [Democratizing LLMs for Low-Resource Languages by Leveraging their English Dominant Abilities with Linguistically-Diverse Prompts](https://mlsanity.com/paper/2306.11372/) (2023)
- [Rethinking Machine Ethics -- Can LLMs Perform Moral Reasoning through the Lens of Moral Theories?](https://mlsanity.com/paper/2308.15399/) (2023)

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

- [Large Language Model Reasoning Failures](https://mlsanity.com/paper/2602.06176/) (2026)
- [The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Models](https://mlsanity.com/paper/2406.11096/) (2024)
- [Large language models for artificial general intelligence (AGI): A survey of foundational principles and approaches](https://mlsanity.com/paper/2501.03151/) (2025)
- [Charting the Landscape of African NLP: Mapping Progress and Shaping the Road Ahead](https://mlsanity.com/paper/2505.21315/) (2025)
- [Algorithmic Fidelity of Large Language Models in Generating Synthetic German Public Opinions: A Case Study](https://mlsanity.com/paper/2412.13169/) (2024)
- [MAKIEval: A Multilingual Automatic WiKidata-based Framework for Cultural Awareness Evaluation for LLMs](https://mlsanity.com/paper/2505.21693/) (2025)
- [From RAG to Agentic RAG for Faithful Islamic Question Answering](https://mlsanity.com/paper/2601.07528/) (2026)
- [Are Large Language Models Chameleons? An Attempt to Simulate Social Surveys](https://mlsanity.com/paper/2405.19323/) (2024)
- [Meta-Cultural Competence: Climbing the Right Hill of Cultural Awareness](https://mlsanity.com/paper/2502.09637/) (2025)
- [Analyzing Political Bias in LLMs via Target-Oriented Sentiment Classification](https://mlsanity.com/paper/2505.19776/) (2025)
- [SPICA: Retrieving Scenarios for Pluralistic In-Context Alignment](https://mlsanity.com/paper/2411.10912/) (2024)
- [Made-in China, Thinking in America:U.S. Values Persist in Chinese LLMs](https://mlsanity.com/paper/2512.13723/) (2025)
- [Histoires Morales: A French Dataset for Assessing Moral Alignment](https://mlsanity.com/paper/2501.17117/) (2025)
- [Uncovering Cultural Representation Disparities in Vision-Language Models](https://mlsanity.com/paper/2505.14729/) (2025)
- [Evaluation of Cultural Competence of Vision-Language Models](https://mlsanity.com/paper/2505.22793/) (2025)
- [EtiCor++: Towards Understanding Etiquettical Bias in LLMs](https://mlsanity.com/paper/2506.08488/) (2025)
- [Exploring Cultural Variations in Moral Judgments with Large Language Models](https://mlsanity.com/paper/2506.12433/) (2025)
- [IndicSafe: A Benchmark for Evaluating Multilingual LLM Safety in South Asia](https://mlsanity.com/paper/2603.17915/) (2026)
- [How Toxic Can You Get? Search-based Toxicity Testing for Large Language Models](https://mlsanity.com/paper/2501.01741/) (2025)
- [Do Large Language Models Know Folktales? A Case Study of Yokai in Japanese Folktales](https://mlsanity.com/paper/2506.03619/) (2025)
- [A Game-Theoretic Negotiation Framework for Cross-Cultural Consensus in LLMs](https://mlsanity.com/paper/2506.13245/) (2025)
- ["Amazing, They All Lean Left" -- Analyzing the Political Temperaments of Current LLMs](https://mlsanity.com/paper/2507.08027/) (2025)
- [Pluralistic Alignment for Healthcare: A Role-Driven Framework](https://mlsanity.com/paper/2509.10685/) (2025)
- [Diverse Human Value Alignment for Large Language Models via Ethical Reasoning](https://mlsanity.com/paper/2511.00379/) (2025)
- [Structuring the Space of Sociotechnical Alignment](https://mlsanity.com/paper/2607.01250/) (2026)
- [AI Ethics by Design: Implementing Customizable Guardrails for Responsible AI Development](https://mlsanity.com/paper/2411.14442/) (2024)
- [Beyond English: Evaluating Automated Measurement of Moral Foundations in Non-English Discourse with a Chinese Case Study](https://mlsanity.com/paper/2502.02451/) (2025)
- [Hedging and Non-Affirmation: Quantifying LLM Alignment on Questions of Human Rights](https://mlsanity.com/paper/2502.19463/) (2025)
- [What if I ask in textitalia lingua? Measuring Functional Similarity Across Languages](https://mlsanity.com/paper/2509.04032/) (2025)
- [JUBAKU: An Adversarial Benchmark for Exposing Culturally Grounded Stereotypes in Japanese LLMs](https://mlsanity.com/paper/2603.20581/) (2026)

## Abstract (arXiv)

Ethical reasoning is a crucial skill for Large Language Models (LLMs). However, moral values are not universal, but rather influenced by language and culture. This paper explores how three prominent LLMs -- GPT-4, ChatGPT, and Llama2-70B-Chat -- perform ethical reasoning in different languages and if their moral judgement depend on the language in which they are prompted. We extend the study of ethical reasoning of LLMs by Rao et al. (2023) to a multilingual setup following their framework of probing LLMs with ethical dilemmas and policies from three branches of normative ethics: deontology, virtue, and consequentialism. We experiment with six languages: English, Spanish, Russian, Chinese, Hindi, and Swahili. We find that GPT-4 is the most consistent and unbiased ethical reasoner across languages, while ChatGPT and Llama2-70B-Chat show significant moral value bias when we move to languages other than English. Interestingly, the nature of this bias significantly vary across languages for all LLMs, including GPT-4.