mlsanityData to 14 Oct 2026

VITAL: A New Dataset for Benchmarking Pluralistic Alignment in Healthcare

arXiv 2502.13775 ↗First posted 19 Feb 2025cs.CL cs.AI cs.LGcited by 17

On the map: LLM alignment / RLHF / preference optimisation → Medical LLM alignment

Abstract (arXiv)

Alignment techniques have become central to ensuring that Large Language Models (LLMs) generate outputs consistent with human values. However, existing alignment paradigms often model an averaged or monolithic preference, failing to account for the diversity of perspectives across cultures, demographics, and communities. This limitation is particularly critical in health-related scenarios, where plurality is essential due to the influence of culture, religion, personal values, and conflicting opinions. Despite progress in pluralistic alignment, no prior work has focused on health, likely due to the unavailability of publicly available datasets. To address this gap, we introduce VITAL, a new benchmark dataset comprising 13.1K value-laden situations and 5.4K multiple-choice questions focused on health, designed to assess and benchmark pluralistic alignment methodologies. Through extensive evaluation of eight LLMs of varying sizes, we demonstrate that existing pluralistic alignment techniques fall short in effectively accommodating diverse healthcare beliefs, underscoring the need for tailored AI alignment in specific domains. This work highlights the limitations of current approaches and lays the groundwork for developing health-specific alignment solutions.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Placed in Medical LLM alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 34 of its 74 references that are in the map. First posted on arXiv 19 Feb 2025.

Builds on

34 of 74 references.

References · 34

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2017Proximal Policy Optimization Algorithmscited by 15,215
  4. 2024The Llama 3 Herd of Modelscited by 14,715
  5. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  6. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  7. 2017Deep reinforcement learning from human preferencescited by 3,912
  8. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  9. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  10. 2020Learning to summarize from human feedbackcited by 2,588
  11. 2022Red Teaming Language Models with Language Modelscited by 1,026
  12. 2021Ethical and social risks of harm from Language Modelscited by 966
22 more
  1. 2023ChatGPT Outperforms Crowd-Workers for Text-Annotation Taskscited by 870
  2. 2023Whose Opinions Do Language Models Reflect?cited by 773
  3. 2022Out of One, Many: Using Language Models to Simulate Human Samplescited by 752
  4. 2020Artificial Intelligence, Values and Alignmentcited by 448
  5. 2023Towards Measuring the Representation of Subjective Global Opinions in Language Modelscited by 437
  6. 2023Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignmentcited by 401
  7. 2023MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoningcited by 316
  8. 2021Symbolic Knowledge Distillation: from General Language Models to Commonsense Modelscited by 270
  9. 2023Large Language Model Alignment: A Surveycited by 243
  10. 2021Get Your Vitamin C! Robust Fact Verification with Contrastive Evidencecited by 225
  11. 2024From Persona to Personalization: A Survey on Role-Playing Language Agentscited by 212
  12. 2024Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalizationcited by 208
  13. 2023The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientationcited by 189
  14. 2024Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaborationcited by 113
  15. 2024What Evidence Do Language Models Find Convincing?cited by 75
  16. 2024LLM Discussion: Enhancing the Creativity of Large Language Models via Discussion Framework and Role-Playcited by 66
  17. 2023Flames: Benchmarking Value Alignment of LLMs in Chinesecited by 37
  18. 2023Assessing LLMs for Moral Value Pluralismcited by 34
  19. 2024From Distributional to Overton Pluralism: Investigating Large Language Model Alignmentcited by 33
  20. 2023Exploring Zero and Few-shot Techniques for Intent Classificationcited by 21
  21. 2024Cultural Palette: Pluralising Culture Alignment via Multi-agent Palettecited by 16
  22. 2024Evaluating Moral Beliefs across LLMs through a Pluralistic Frameworkcited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 7; 2026: 10.

17 papers.

Sort:

By area:

  1. 2025A Survey on Progress in LLM Alignment from the Perspective of Reward Designcited by 15
  2. 2025MedSentry: Understanding and Mitigating Safety Risks in Medical LLM Multi-Agent Systemscited by 9
  3. 2026COLD-Steer: Steering Large Language Models via In-Context One-step Learning Dynamicscited by 8
  4. 2025Benchmarking Overton Pluralism in LLMscited by 7
  5. 2025Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectivescited by 5
  6. 2025XGUARD: A Graded Benchmark for Evaluating Safety Failures of Large Language Models on Extremist Contentcited by 3
  7. 2025Pluralistic Alignment for Healthcare: A Role-Driven Frameworkcited by 2
  8. 2026What Does the AI Doctor Value? Auditing Pluralism in the Clinical Ethics of Language Modelscited by 2
  9. 2026Structuring the Space of Sociotechnical Alignmentcited by 2
  10. 2025Classical AI vs. LLMs for Decision-Maker Alignment in Health Insurance Choicescited by 1
  11. 2026VISPA: Pluralistic Alignment via Automatic Value Selection and Activationcited by 1
  12. 2026Jailbreaking Large Language Models with Morality Attackscited by 1
5 more
  1. 2026Not All Subjectivity Is the Same! Defining Desiderata for the Evaluation of Subjectivity in NLPcited by 0
  2. 2026A Roadmap to Impactful Pluralistic Alignment Researchcited by 0
  3. 2026CultureMINE: Datasets and Methods for Improving the Cultural Capabilities of NLP Systemscited by 0
  4. 2026Narrowing the Horizon: Quantifying Topic Saliency Shifts in Generative Monoculturecited by 0
  5. 2026Demographic Pluralism: Inference-Time Modeling of Pluralistic Human Preference Distributionscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Aligning Large Language Models with Healthcare Stakeholders: A Pathway to Trustworthy AI Integration
  2. 2024A Roadmap to Pluralistic Alignment
  3. 2026PLURAL: A Global Dataset for Value Alignment
  4. 2026ClinAlign: Scaling Healthcare Alignment from Clinician Preference
  5. 2024Systematic Characterization of the Effectiveness of Alignment in Large Language Models for Categorical Decisions
  6. 2025Operationalizing Pluralistic Values in Large Language Model Alignment Reveals Trade-offs in Safety, Inclusivity, and Model Behavior
  7. 2026A Human-Centric Pipeline for Aligning Large Language Models with Chinese Medical Ethics
  8. 2026Alignment Plausibility: A New Standard for Assuring AI in Healthcare