mlsanityData to 7 Oct 2026

PLURAL: A Global Dataset for Value Alignment

arXiv 2607.08034 ↗First posted 9 Jul 2026cs.CL cs.AI cs.CYcited by 1

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

Abstract (arXiv)

Large language models (LLMs) are used worldwide, yet disproportionately reflect Western values, limiting their ability to represent diverse value systems. We introduce PLURAL, a large-scale, value-focused preference dataset grounded in the Integrated Values Survey (IVS), a nationally representative survey spanning 92 countries. Using a two-stage generation pipeline, we transform survey responses into synthetic preference triplets that preserve normative value signals while producing realistic scenarios. We release an initial version of PLURAL containing ~500,000 preference triplets representing people in 20 diverse countries. We evaluate PLURAL in three ways: (i) dataset-level validation showing that it preserves both cross-country value differences and within-country diversity from the original survey; (ii) automated evaluation showing that training on PLURAL improves alignment with target countries' cultural profiles, reducing mean absolute error by up to 27.7% relative to strong baselines; and (iii) blind human evaluation with 176 evaluators in India, Brazil, and Japan, who judge PLURAL-aligned responses as more representative of their national values. Together, these results show that PLURAL contains learnable signal for value steering, offering a scalable resource for pluralistic alignment. Dataset: https://huggingface.co/datasets/agdhruv/plural-alignment

Key facts. Cited by 1 paper in the map (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 37 of its 54 references that are in the map. First posted on arXiv 9 Jul 2026.

Builds on

37 of 54 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025What's In My Human Feedback? Learning Interpretable Descriptions of Preference Data30 Oct
  2. 2025CARE: Multilingual Human Preference Learning for Cultural Awareness7 Apr
  3. 2024Self-Pluralising Culture Alignment for Large Language Models16 Oct
  4. 2024Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration22 Jun
  5. 2024The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models24 Apr

Other references · 32

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  3. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  4. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  5. 2024Scaling Synthetic Data Creation with 1,000,000,000 Personascited by 397
  6. 2024tinyBenchmarks: evaluating LLMs with fewer examplescited by 295
  7. 2024PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preferencecited by 252
  8. 2023Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Studycited by 203
  9. 2024Towards Measuring and Modeling "Culture" in LLMs: A Surveycited by 166
  10. 2023Having Beer after Prayer? Measuring Cultural Bias in Large Language Modelscited by 153
  11. 2022The Ghost in the Machine has an American accent: value conflict in GPT-3cited by 105
  12. 2024Is Temperature the Creativity Parameter of Large Language Models?cited by 92
20 more
  1. 2025Jointly Reinforcing Diversity and Quality in Language Model Generationscited by 79
  2. 2024AI Suggestions Homogenize Writing Toward Western Styles and Diminish Cultural Nuancescited by 59
  3. 2023AI's Regimes of Representation: A Community-centered Study of Text-to-Image Models in South Asiacited by 54
  4. 2025Mind the Value-Action Gap: Do LLMs Act in Alignment with Their Values?cited by 49
  5. 2025Values in the Wild: Discovering and Analyzing Values in Real-World Language Model Interactionscited by 47
  6. 2024CulturalBench: A Robust, Diverse, and Challenging Cultural Benchmark by Human-AI CulturalTeamingcited by 27
  7. 2022Cultural Incongruencies in Artificial Intelligencecited by 21
  8. 2025Post-training Large Language Models for Diverse High-Quality Responsescited by 19
  9. 2024CIVICS: Building a Dataset for Examining Culturally-Informed Values in Large Language Modelscited by 16
  10. 2024Cultural Palette: Pluralising Culture Alignment via Multi-agent Palettecited by 14
  11. 2025ValuesRAG: Enhancing Cultural Alignment Through Retrieval-Augmented Contextual Learningcited by 10
  12. 2025Llama-3-Nanda-10B-Chat: An Open Generative Large Language Model for Hindicited by 10
  13. 2024Growing a Tail: Increasing Output Diversity in Large Language Modelscited by 9
  14. 2025From Surveys to Narratives: Rethinking Cultural Value Adaptation in LLMscited by 9
  15. 2025Fluent but Foreign: Even Regional LLMs Lack Cultural Alignmentcited by 9
  16. 2025Can LLMs Express Personality Across Cultures? Introducing CulturalPersonas for Evaluating Trait Alignmentcited by 9
  17. 2025Asking a Language Model for Diverse Responsescited by 9
  18. 2025Do Large Language Models Truly Understand Cross-cultural Differences?cited by 5
  19. 2025LLMs Homogenize Values in Constructive Arguments on Value-Laden Topicscited by 3
  20. 2026SEA-Guard: Culturally Grounded Multilingual Safeguard for Southeast Asiacited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Cultural Divergence Preservation: Diagnosing Flattening and Caricature in LLM-Simulated Survey Populationscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026DVMap: Fine-Grained Pluralistic Value Alignment via High-Consensus Demographic-Value Mapping
  2. 2026Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural Alignment
  3. 2025Benchmarking Multi-National Value Alignment for Large Language Models
  4. 2025Cultivating Pluralism In Algorithmic Monoculture: The Community Alignment Dataset
  5. 2026Pancasila-Dilemmas: Evaluating Large Language Models on Indonesian Human Value Dilemmas Grounded in Pancasila
  6. 2025Operationalizing Pluralistic Values in Large Language Model Alignment Reveals Trade-offs in Safety, Inclusivity, and Model Behavior
  7. 2026LKValues: Aligning Large Language Models with Sri Lankan Societal Values
  8. 2026VISPA: Pluralistic Alignment via Automatic Value Selection and Activation