# Exploring Multilingual Concepts of Human Value in Large Language Models: Is Value Alignment Consistent, Transferable and Controllable across Languages?

arXiv: https://arxiv.org/abs/2402.18120 · HTML: https://mlsanity.com/paper/2402.18120/

## Key facts

- Cited by 24 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 34 of its 48 references that are in the map.
- First posted on arXiv 28 Feb 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 34)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [Cross-lingual Language Model Pretraining](https://mlsanity.com/paper/1901.07291/) (2019)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [The State and Fate of Linguistic Diversity and Inclusion in the NLP World](https://mlsanity.com/paper/2004.09095/) (2020)
- [Aligning AI With Shared Human Values](https://mlsanity.com/paper/2008.02275/) (2020)
- [DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models](https://mlsanity.com/paper/2306.11698/) (2023)
- [Low-Resource Languages Jailbreak GPT-4](https://mlsanity.com/paper/2310.02446/) (2023)
- [Large Language Model Alignment: A Survey](https://mlsanity.com/paper/2309.15025/) (2023)
- [InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training](https://mlsanity.com/paper/2007.07834/) (2020)
- [Challenges and Strategies in Cross-Cultural NLP](https://mlsanity.com/paper/2203.10020/) (2022)
- [Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Study](https://mlsanity.com/paper/2303.17466/) (2023)
- [Evaluating Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2310.19736/) (2023)
- [Systematic Inequalities in Language Technology Performance across the World's Languages](https://mlsanity.com/paper/2110.06733/) (2021)
- [Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Models](https://mlsanity.com/paper/2310.10378/) (2023)
- [Don't Trust ChatGPT when Your Question is not in English: A Study of Multilingual Abilities and Types of LLMs](https://mlsanity.com/paper/2305.16339/) (2023)
- [The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts](https://mlsanity.com/paper/2401.13136/) (2024)
- [Aligning Large Language Models with Human Preferences through Representation Engineering](https://mlsanity.com/paper/2312.15997/) (2023)
- [Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems](https://mlsanity.com/paper/2401.05778/) (2024)
- [Self-Detoxifying Language Models via Toxification Reversal](https://mlsanity.com/paper/2310.09573/) (2023)
- [Speaking Multiple Languages Affects the Moral Bias of Language Models](https://mlsanity.com/paper/2211.07733/) (2022)

## Built on by (most cited first, 24 of 24)

- [How Well Do LLMs Represent Values Across Cultures? Empirical Analysis of LLM Responses Based on Hofstede Cultural Dimensions](https://mlsanity.com/paper/2406.14805/) (2024)
- [Self-Pluralising Culture Alignment for Large Language Models](https://mlsanity.com/paper/2410.12971/) (2024)
- [Finding Visual Task Vectors](https://mlsanity.com/paper/2404.05729/) (2024)
- [Internal Value Alignment in Large Language Models through Controlled Value Vector Activation](https://mlsanity.com/paper/2507.11316/) (2025)
- [Does Cross-Cultural Alignment Change the Commonsense Morality of Language Models?](https://mlsanity.com/paper/2406.16316/) (2024)
- [ConTrans: Weak-to-Strong Alignment Engineering via Concept Transplantation](https://mlsanity.com/paper/2405.13578/) (2024)
- [Through the Prism of Culture: Evaluating LLMs' Understanding of Indian Subcultures and Traditions](https://mlsanity.com/paper/2501.16748/) (2025)
- [Beg to Differ: Understanding Reasoning-Answer Misalignment Across Languages](https://mlsanity.com/paper/2512.22712/) (2025)
- [Annotation-Efficient Language Model Alignment via Diverse and Representative Response Texts](https://mlsanity.com/paper/2405.13541/) (2024)
- [Do Large Language Models Know Folktales? A Case Study of Yokai in Japanese Folktales](https://mlsanity.com/paper/2506.03619/) (2025)
- [Evaluating Modern Large Language Models on Low-Resource and Morphologically Rich Languages:A Cross-Lingual Benchmark Across Cantonese, Japanese, and Turkish](https://mlsanity.com/paper/2511.10664/) (2025)
- [Language Shapes Mental Health Evaluations in Large Language Models](https://mlsanity.com/paper/2603.06910/) (2026)
- [Measuring Human Value Expression in Social Media Texts: Calibrated LLM Annotation and Encoder Transfer](https://mlsanity.com/paper/2606.11018/) (2026)
- [Structuring the Space of Sociotechnical Alignment](https://mlsanity.com/paper/2607.01250/) (2026)
- [Layered LLM Defenses as an Ensemble: Access Tiers, Inference Cost, and the Measured Failure Correlation Between Defense Layers](https://mlsanity.com/paper/2608.28327/) (2026)
- [Toward Cultural Interpretability: A Linguistic Anthropological Framework for Describing and Evaluating Large Language Models (LLMs)](https://mlsanity.com/paper/2411.05200/) (2024)
- [Do LLMs Know They Are Being Tested? Evaluation Awareness and Incentive-Sensitive Failures in GPT-OSS-20B](https://mlsanity.com/paper/2510.08624/) (2025)
- [VISPA: Pluralistic Alignment via Automatic Value Selection and Activation](https://mlsanity.com/paper/2601.12758/) (2026)
- [DVMap: Fine-Grained Pluralistic Value Alignment via High-Consensus Demographic-Value Mapping](https://mlsanity.com/paper/2605.14420/) (2026)
- [Beyond Value Benchmarks: Measuring Value-Structure Alignment in Large Language Models via Symmetric Q-Sorts](https://mlsanity.com/paper/2606.21939/) (2026)
- [ExpertIVS: Sociological Expert Driven Individual Value Simulation in Large Language Models](https://mlsanity.com/paper/2608.20355/) (2026)
- [CultureMINE: Datasets and Methods for Improving the Cultural Capabilities of NLP Systems](https://mlsanity.com/paper/2609.22494/) (2026)
- [FineWeb-CLaR: Culture, Language, and Region Annotations for Benchmark-Aligned Corpus Auditing](https://mlsanity.com/paper/2609.25298/) (2026)
- [PlurVA-LLM-2026 Shared Task Track-1: Pluralistic Value Alignment in LLMs via Multilingual Fine-Tuning and Threshold Calibration](https://mlsanity.com/paper/2609.32382/) (2026)

## Abstract (arXiv)

Prior research has revealed that certain abstract concepts are linearly represented as directions in the representation space of LLMs, predominantly centered around English. In this paper, we extend this investigation to a multilingual context, with a specific focus on human values-related concepts (i.e., value concepts) due to their significance for AI safety. Through our comprehensive exploration covering 7 types of human values, 16 languages and 3 LLM series with distinct multilinguality (e.g., monolingual, bilingual and multilingual), we first empirically confirm the presence of value concepts within LLMs in a multilingual format. Further analysis on the cross-lingual characteristics of these concepts reveals 3 traits arising from language resource disparities: cross-lingual inconsistency, distorted linguistic relationships, and unidirectional cross-lingual transfer between high- and low-resource languages, all in terms of value concepts. Moreover, we validate the feasibility of cross-lingual control over value alignment capabilities of LLMs, leveraging the dominant language as a source language. Ultimately, recognizing the significant impact of LLMs' multilinguality on our results, we consolidate our findings and provide prudent suggestions on the composition of multilingual data for LLMs pre-training.