# One Model, Many Morals: Uncovering Cross-Linguistic Misalignments in Computational Moral Reasoning

arXiv: https://arxiv.org/abs/2509.21443 · HTML: https://mlsanity.com/paper/2509.21443/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 36 of its 84 references that are in the map.
- First posted on arXiv 25 Sep 2025.

## Placed in

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

## Builds on (most cited first, 30 of 36)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Tulu 3: Pushing Frontiers in Open Language Model Post-Training](https://mlsanity.com/paper/2411.15124/) (2024)
- [Aligning AI With Shared Human Values](https://mlsanity.com/paper/2008.02275/) (2020)
- [Language-agnostic BERT Sentence Embedding](https://mlsanity.com/paper/2007.01852/) (2020)
- [Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference](https://mlsanity.com/paper/2412.13663/) (2024)
- [Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs](https://mlsanity.com/paper/2503.01743/) (2025)
- [2 OLMo 2 Furious](https://mlsanity.com/paper/2501.00656/) (2024)
- [Language Model Tokenizers Introduce Unfairness Between Languages](https://mlsanity.com/paper/2305.15425/) (2023)
- [Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation](https://mlsanity.com/paper/2412.03304/) (2024)
- [Towards Measuring and Modeling "Culture" in LLMs: A Survey](https://mlsanity.com/paper/2403.15412/) (2024)
- [Having Beer after Prayer? Measuring Cultural Bias in Large Language Models](https://mlsanity.com/paper/2305.14456/) (2023)
- [Infini-gram: Scaling Unbounded n-gram Language Models to a Trillion Tokens](https://mlsanity.com/paper/2401.17377/) (2024)
- [A Survey Of Cross-lingual Word Embedding Models](https://mlsanity.com/paper/1706.04902/) (2017)
- [Can Machines Learn Morality? The Delphi Experiment](https://mlsanity.com/paper/2110.07574/) (2021)
- [Cultural Alignment in Large Language Models: An Explanatory Analysis Based on Hofstede's Cultural Dimensions](https://mlsanity.com/paper/2309.12342/) (2023)
- [CultureBank: An Online Community-Driven Knowledge Base Towards Culturally Aware Language Technologies](https://mlsanity.com/paper/2404.15238/) (2024)
- [When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment](https://mlsanity.com/paper/2210.01478/) (2022)
- [A Survey on Multilingual Large Language Models: Corpora, Alignment, and Bias](https://mlsanity.com/paper/2404.00929/) (2024)
- [Understanding and Mitigating Language Confusion in LLMs](https://mlsanity.com/paper/2406.20052/) (2024)
- [MoralBench: Moral Evaluation of LLMs](https://mlsanity.com/paper/2406.04428/) (2024)
- [You don't need a personality test to know these models are unreliable: Assessing the Reliability of Large Language Models on Psychometric Instruments](https://mlsanity.com/paper/2311.09718/) (2023)
- [Not All Countries Celebrate Thanksgiving: On the Cultural Dominance in Large Language Models](https://mlsanity.com/paper/2310.12481/) (2023)
- [A Survey on Large Language Models with Multilingualism: Recent Advances and New Frontiers](https://mlsanity.com/paper/2405.10936/) (2024)
- [Rethinking Machine Ethics -- Can LLMs Perform Moral Reasoning through the Lens of Moral Theories?](https://mlsanity.com/paper/2308.15399/) (2023)
- [OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens](https://mlsanity.com/paper/2504.07096/) (2025)
- [Denevil: Towards Deciphering and Navigating the Ethical Values of Large Language Models via Instruction Learning](https://mlsanity.com/paper/2310.11053/) (2023)
- [TeachTune: Reviewing Pedagogical Agents Against Diverse Student Profiles with Simulated Students](https://mlsanity.com/paper/2410.04078/) (2024)
- [Normative Evaluation of Large Language Models with Everyday Moral Dilemmas](https://mlsanity.com/paper/2501.18081/) (2025)

## Built on by (most cited first, 4 of 4)

- [EvalMORAAL: Interpretable Chain-of-Thought and LLM-as-Judge Evaluation for Moral Alignment in Large Language Models](https://mlsanity.com/paper/2510.05942/) (2025)
- [Towards Cross-lingual Values Judgment: A Consensus-Pluralism Perspective](https://mlsanity.com/paper/2602.17283/) (2026)
- [Do Large Language Models Encode Institutional Experience? Evidence from Cross-Linguistic Moral Reasoning Under Ambiguity](https://mlsanity.com/paper/2605.30934/) (2026)
- [MET: Theory-Grounded and Culture-Aware Multilingual Moral Reasoning](https://mlsanity.com/paper/2607.11736/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) are increasingly deployed across multilingual and multicultural settings, yet it remains unclear whether changing language leads models to adopt community-specific moral reasoning or merely changes how shared learned abstractions are expressed. We conduct a controlled multilingual evaluation across six geographically, culturally, and linguistically diverse languages (Arabic, Chinese, English, Hindi, Russian, and Spanish), using parallel moral reasoning benchmarks with English-origin, Chinese-origin, and natively elicited ground-truth judgments. Across 13 open-weight LLMs spanning 2B-70B parameters, we find substantial cross-lingual divergence in moral judgments, with English generally achieving the highest performance even when ground-truth judgments originate in Chinese or are collected natively in each language. Yet the reasoning underlying these divergent judgments is considerably more convergent: Utilitarianism dominates in five of six languages, reasoning follows broadly shared stages, and language-specific moral-value associations correspond only sparsely and inconsistently to values measured in the corresponding human communities. Finally, a large-scale OLMoTrace analysis of pretraining data sources reveals little direct reproduction of training text across languages, while the corpus composition, training stage, and cultural provenance of retrieved training evidence vary substantially by response language. Thus, similar moral reasoning structures emerge even from heterogeneous and often linguistically localized training evidence. Our findings, collectively, reveal a central disconnect in multilingual moral reasoning: language changes models' moral judgments and the training evidence associated with their reasoning, but does not correspondingly localize the moral abstractions they apply.