# Do Multilingual Language Models Capture Differing Moral Norms?

arXiv: https://arxiv.org/abs/2203.09904 · HTML: https://mlsanity.com/paper/2203.09904/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 17 references that are in the map.
- First posted on arXiv 18 Mar 2022.

## Builds on (most cited first, 14 of 14)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Aligning AI With Shared Human Values](https://mlsanity.com/paper/2008.02275/) (2020)
- [Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation](https://mlsanity.com/paper/2004.09813/) (2020)
- [AraBERT: Transformer-based Model for Arabic Language Understanding](https://mlsanity.com/paper/2003.00104/) (2020)
- [Symbolic Knowledge Distillation: from General Language Models to Commonsense Models](https://mlsanity.com/paper/2110.07178/) (2021)
- [Commonsense Knowledge Mining from Pretrained Models](https://mlsanity.com/paper/1909.00505/) (2019)
- [Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do](https://mlsanity.com/paper/2103.11790/) (2021)
- [German's Next Language Model](https://mlsanity.com/paper/2010.10906/) (2020)
- [On the Language Neutrality of Pre-trained Multilingual Representations](https://mlsanity.com/paper/2004.05160/) (2020)
- [RobeCzech: Czech RoBERTa, a monolingual contextualized language representation model](https://mlsanity.com/paper/2105.11314/) (2021)
- [Combining Static and Contextualised Multilingual Embeddings](https://mlsanity.com/paper/2203.09326/) (2022)

## Built on by (most cited first, 15 of 15)

- [Emergent social conventions and collective bias in LLM populations](https://mlsanity.com/paper/2410.08948/) (2024)
- [Knowledge of cultural moral norms in large language models](https://mlsanity.com/paper/2306.01857/) (2023)
- [Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers](https://mlsanity.com/paper/2404.04925/) (2024)
- [Emergence of Social Norms in Generative Agent Societies: Principles and Architecture](https://mlsanity.com/paper/2403.08251/) (2024)
- [Does Moral Code Have a Moral Code? Probing Delphi's Moral Philosophy](https://mlsanity.com/paper/2205.12771/) (2022)
- [Values, Ethics, Morals? On the Use of Moral Concepts in NLP Research](https://mlsanity.com/paper/2310.13915/) (2023)
- [Bridging the Language Gap: Dynamic Learning Strategies for Improving Multilingual Performance in LLMs](https://mlsanity.com/paper/2305.17740/) (2023)
- [Can Agents Spontaneously Form a Society? Introducing a Novel Architecture for Generative Multi-Agents to Elicit Social Emergence](https://mlsanity.com/paper/2409.06750/) (2024)
- [Large Language Models as Mirrors of Societal Moral Standards](https://mlsanity.com/paper/2412.00956/) (2024)
- [Monolingual and Multilingual Misinformation Detection for Low-Resource Languages: A Comprehensive Survey](https://mlsanity.com/paper/2410.18390/) (2024)
- [Exploring Cultural Variations in Moral Judgments with Large Language Models](https://mlsanity.com/paper/2506.12433/) (2025)
- [Visual moral inference and communication](https://mlsanity.com/paper/2504.11473/) (2025)
- [Probabilistic Aggregation and Targeted Embedding Optimization for Collective Moral Reasoning in Large Language Models](https://mlsanity.com/paper/2506.14625/) (2025)
- [Lost in the Tower of Babel: The Adverse Effects of Incidental Multilingualism in LLMs](https://mlsanity.com/paper/2605.01224/) (2026)
- [PAVE: A Cognitive Architecture for Legitimate Violation in Generative Agent Societies](https://mlsanity.com/paper/2605.19351/) (2026)

## Abstract (arXiv)

Massively multilingual sentence representations are trained on large corpora of uncurated data, with a very imbalanced proportion of languages included in the training. This may cause the models to grasp cultural values including moral judgments from the high-resource languages and impose them on the low-resource languages. The lack of data in certain languages can also lead to developing random and thus potentially harmful beliefs. Both these issues can negatively influence zero-shot cross-lingual model transfer and potentially lead to harmful outcomes. Therefore, we aim to (1) detect and quantify these issues by comparing different models in different languages, (2) develop methods for improving undesirable properties of the models. Our initial experiments using the multilingual model XLM-R show that indeed multilingual LMs capture moral norms, even with potentially higher human-agreement than monolingual ones. However, it is not yet clear to what extent these moral norms differ between languages.