mlsanityData to 14 Oct 2026

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

arXiv 2402.18120 ↗First posted 28 Feb 2024cs.CLcited by 24

On the map: LLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment

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.

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.

Builds on

34 of 48 references.

Closest ancestors · 1

Same direction, newest first

  1. 2020Aligning AI With Shared Human Values5 Aug

Other references · 33

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  3. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  4. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 3,104
  5. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,975
  6. 2022BLOOM: A 176B-Parameter Open-Access Multilingual Language Modelcited by 1,984
  7. 2020mT5: A massively multilingual pre-trained text-to-text transformercited by 1,818
  8. 2023Representation Engineering: A Top-Down Approach to AI Transparencycited by 1,336
  9. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,302
  10. 2020RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Modelscited by 1,255
  11. 2019Cross-lingual Language Model Pretrainingcited by 1,090
  12. 2021A General Language Assistant as a Laboratory for Alignmentcited by 1,055
21 more
  1. 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 924
  2. 2020The State and Fate of Linguistic Diversity and Inclusion in the NLP Worldcited by 798
  3. 2023DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Modelscited by 518
  4. 2023Low-Resource Languages Jailbreak GPT-4cited by 309
  5. 2023Large Language Model Alignment: A Surveycited by 243
  6. 2020InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Trainingcited by 237
  7. 2022Challenges and Strategies in Cross-Cultural NLPcited by 218
  8. 2023Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Studycited by 206
  9. 2023Evaluating Large Language Models: A Comprehensive Surveycited by 202
  10. 2021Systematic Inequalities in Language Technology Performance across the World's Languagescited by 120
  11. 2023Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Modelscited by 118
  12. 2023Don't Trust ChatGPT when Your Question is not in English: A Study of Multilingual Abilities and Types of LLMscited by 104
  13. 2024The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contextscited by 94
  14. 2023Aligning Large Language Models with Human Preferences through Representation Engineeringcited by 71
  15. 2024Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systemscited by 66
  16. 2023Self-Detoxifying Language Models via Toxification Reversalcited by 46
  17. 2022Speaking Multiple Languages Affects the Moral Bias of Language Modelscited by 34
  18. 2023Language Representation Projection: Can We Transfer Factual Knowledge across Languages in Multilingual Language Models?cited by 19
  19. 2023Separating form and meaning: Using self-consistency to quantify task understanding across multiple sensescited by 15
  20. 2023Values, Ethics, Morals? On the Use of Moral Concepts in NLP Researchcited by 14
  21. 2023Unveiling Multilinguality in Transformer Models: Exploring Language Specificity in Feed-Forward Networkscited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 7; 2025: 6; 2026: 11.

24 papers.

Sort:

By area:

  1. 2024How Well Do LLMs Represent Values Across Cultures? Empirical Analysis of LLM Responses Based on Hofstede Cultural Dimensionscited by 52
  2. 2024Self-Pluralising Culture Alignment for Large Language Modelscited by 31
  3. 2024Finding Visual Task Vectorscited by 24
  4. 2025Internal Value Alignment in Large Language Models through Controlled Value Vector Activationcited by 16
  5. 2024Does Cross-Cultural Alignment Change the Commonsense Morality of Language Models?cited by 10
  6. 2024ConTrans: Weak-to-Strong Alignment Engineering via Concept Transplantationcited by 8
  7. 2025Through the Prism of Culture: Evaluating LLMs' Understanding of Indian Subcultures and Traditionscited by 4
  8. 2025Beg to Differ: Understanding Reasoning-Answer Misalignment Across Languagescited by 4
  9. 2024Annotation-Efficient Language Model Alignment via Diverse and Representative Response Textscited by 3
  10. 2025Do Large Language Models Know Folktales? A Case Study of Yokai in Japanese Folktalescited by 2
  11. 2025Evaluating Modern Large Language Models on Low-Resource and Morphologically Rich Languages:A Cross-Lingual Benchmark Across Cantonese, Japanese, and Turkishcited by 2
  12. 2026Language Shapes Mental Health Evaluations in Large Language Modelscited by 2
12 more
  1. 2026Measuring Human Value Expression in Social Media Texts: Calibrated LLM Annotation and Encoder Transfercited by 2
  2. 2026Structuring the Space of Sociotechnical Alignmentcited by 2
  3. 2026Layered LLM Defenses as an Ensemble: Access Tiers, Inference Cost, and the Measured Failure Correlation Between Defense Layerscited by 2
  4. 2024Toward Cultural Interpretability: A Linguistic Anthropological Framework for Describing and Evaluating Large Language Models (LLMs)cited by 1
  5. 2025Do LLMs Know They Are Being Tested? Evaluation Awareness and Incentive-Sensitive Failures in GPT-OSS-20Bcited by 1
  6. 2026VISPA: Pluralistic Alignment via Automatic Value Selection and Activationcited by 1
  7. 2026DVMap: Fine-Grained Pluralistic Value Alignment via High-Consensus Demographic-Value Mappingcited by 1
  8. 2026Beyond Value Benchmarks: Measuring Value-Structure Alignment in Large Language Models via Symmetric Q-Sortscited by 1
  9. 2026ExpertIVS: Sociological Expert Driven Individual Value Simulation in Large Language Modelscited by 0
  10. 2026CultureMINE: Datasets and Methods for Improving the Cultural Capabilities of NLP Systemscited by 0
  11. 2026FineWeb-CLaR: Culture, Language, and Region Annotations for Benchmark-Aligned Corpus Auditingcited by 0
  12. 2026PlurVA-LLM-2026 Shared Task Track-1: Pluralistic Value Alignment in LLMs via Multilingual Fine-Tuning and Threshold Calibrationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Do LLMs Have Values? A Quantitative Analysis and Alignment Framework for Values in Large Language Models
  2. 2025Cultural Value Alignment in Large Language Models: A Prompt-based Analysis of Schwartz Values in Gemini, ChatGPT, and DeepSeek
  3. 2023Heterogeneous Value Alignment Evaluation for Large Language Models
  4. 2025Generative Psycho-Lexical Approach for Constructing Value Systems in Large Language Models
  5. 2024Are the Values of LLMs Structurally Aligned with Humans? A Causal Perspective
  6. 2026Toward a Theory of Value in AI Alignment
  7. 2025C-VARC: A Large-Scale Chinese Value Rule Corpus for Value Alignment of Large Language Models
  8. 2024Language Model Alignment in Multilingual Trolley Problems