mlsanityData to 7 Oct 2026

Cross-cultural value alignment frameworks for responsible AI governance: Evidence from China-West comparative analysis

arXiv 2511.17256 ↗First posted 21 Nov 2025cs.CY cs.CLcited by 0

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

Abstract (arXiv)

As Large Language Models (LLMs) increasingly influence high-stakes decision-making across global contexts, ensuring their alignment with diverse cultural values has become a critical governance challenge. This study presents a Multi-Layered Auditing Platform for Responsible AI that systematically evaluates cross-cultural value alignment in China-origin and Western-origin LLMs through four integrated methodologies: Ethical Dilemma Corpus for assessing temporal stability, Diversity-Enhanced Framework (DEF) for quantifying cultural fidelity, First-Token Probability Alignment for distributional accuracy, and Multi-stAge Reasoning frameworK (MARK) for interpretable decision-making. Our comparative analysis of 20+ leading models, such as Qwen, GPT-4o, Claude, LLaMA, and DeepSeek, reveals universal challenges-fundamental instability in value systems, systematic under-representation of younger demographics, and non-linear relationships between model scale and alignment quality-alongside divergent regional development trajectories. While China-origin models increasingly emphasize multilingual data integration for context-specific optimization, Western models demonstrate greater architectural experimentation but persistent U.S.-centric biases. Neither paradigm achieves robust cross-cultural generalization. We establish that Mistral-series architectures significantly outperform LLaMA3-series in cross-cultural alignment, and that Full-Parameter Fine-Tuning on diverse datasets surpasses Reinforcement Learning from Human Feedback in preserving cultural variation...

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 25 of its 43 references that are in the map. First posted on arXiv 21 Nov 2025.

Builds on

25 of 43 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Cultural Bias and Cultural Alignment of Large Language Models23 Nov
  2. 2020Aligning AI With Shared Human Values5 Aug

Other references · 23

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  3. 2023Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formattingcited by 778
  4. 2023Whose Opinions Do Language Models Reflect?cited by 759
  5. 2022Out of One, Many: Using Language Models to Simulate Human Samplescited by 737
  6. 2023Towards Measuring the Representation of Subjective Global Opinions in Language Modelscited by 424
  7. 2020Social Chemistry 101: Learning to Reason about Social and Moral Normscited by 253
  8. 2023Evaluating the Moral Beliefs Encoded in LLMscited by 211
  9. 2023Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Studycited by 203
  10. 2023Gender bias and stereotypes in Large Language Modelscited by 185
  11. 2019Principles alone cannot guarantee ethical AIcited by 134
  12. 2020Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequencescited by 133
11 more
  1. 2019The Ethics of AI Ethics -- An Evaluation of Guidelinescited by 129
  2. 2024Systematic Biases in LLM Simulations of Debatescited by 98
  3. 2021On Measures of Biases and Harms in NLPcited by 81
  4. 2024WorldValuesBench: A Large-Scale Benchmark Dataset for Multi-Cultural Value Awareness of Language Modelscited by 59
  5. 2025Specializing Large Language Models to Simulate Survey Response Distributions for Global Populationscited by 50
  6. 2024Ethical Reasoning and Moral Value Alignment of LLMs Depend on the Language we Prompt them incited by 45
  7. 2023NBIAS: A Natural Language Processing Framework for Bias Identification in Textcited by 23
  8. 2025The Staircase of Ethics: Probing LLM Value Priorities through Multi-Step Induction to Complex Moral Dilemmascited by 13
  9. 2024Right vs. Right: Can LLMs Make Tough Choices?cited by 6
  10. 2025Beyond Demographics: Enhancing Cultural Value Survey Simulation with Multi-Stage Personality-Driven Cognitive Reasoningcited by 4
  11. 2025Addressing Moral Uncertainty using Large Language Models for Ethical Decision-Makingcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Cultural Value Alignment in Large Language Models: A Prompt-based Analysis of Schwartz Values in Gemini, ChatGPT, and DeepSeek
  2. 2025An Evaluation of Cultural Value Alignment in LLM
  3. 2025Cultural Bias in Large Language Models: Evaluating AI Agents through Moral Questionnaires
  4. 2025Diverse Human Value Alignment for Large Language Models via Ethical Reasoning
  5. 2026Culturally-Grounded Governance for Multilingual Language Models: Rights, Data Boundaries, and Accountable AI Design
  6. 2024LocalValueBench: A Collaboratively Built and Extensible Benchmark for Evaluating Localized Value Alignment and Ethical Safety in Large Language Models
  7. 2025A Game-Theoretic Negotiation Framework for Cross-Cultural Consensus in LLMs
  8. 2025CCD-Bench: Probing Cultural Conflict in Large Language Model Decision-Making