mlsanityData to 7 Oct 2026

ValueCompass: A Framework for Measuring Contextual Value Alignment Between Human and LLMs

arXiv 2409.09586 ↗First posted 15 Sep 2024cs.HC cs.AI cs.CLcited by 20

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

Abstract (arXiv)

As AI systems become more advanced, ensuring their alignment with a diverse range of individuals and societal values becomes increasingly critical. But how can we capture fundamental human values and assess the degree to which AI systems align with them? We introduce ValueCompass, a framework of fundamental values, grounded in psychological theory and a systematic review, to identify and evaluate human-AI alignment. We apply ValueCompass to measure the value alignment of humans and large language models (LLMs) across four real-world scenarios: collaborative writing, education, public sectors, and healthcare. Our findings reveal concerning misalignments between humans and LLMs, such as humans frequently endorse values like "National Security" which were largely rejected by LLMs. We also observe that values differ across scenarios, highlighting the need for context-aware AI alignment strategies. This work provides valuable insights into the design space of human-AI alignment, laying the foundations for developing AI systems that responsibly reflect societal values and ethics.

Key facts. Cited by 20 papers 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 18 of its 46 references that are in the map. First posted on arXiv 15 Sep 2024.

Builds on

18 of 46 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024A Roadmap to Pluralistic Alignment7 Feb
  2. 2023Measuring Value Alignment23 Dec

Other references · 16

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,201
  5. 2018Improving fairness in machine learning systems: What do industry practitioners need?cited by 262
  6. 2020DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detectioncited by 231
  7. 2023Moral Foundations of Large Language Modelscited by 84
  8. 2018Interpretable Deep Learning under Firecited by 74
  9. 2022Moral Mimicry: Large Language Models Produce Moral Rationalizations Tailored to Political Identitycited by 71
  10. 2023Diminished Diversity-of-Thought in a Standard Large Language Modelcited by 43
  11. 2023Deepfakes, Phrenology, Surveillance, and More! A Taxonomy of AI Privacy Riskscited by 31
  12. 2024Farsight: Fostering Responsible AI Awareness During AI Application Prototypingcited by 28
4 more
  1. 2023Geographical Erasure in Language Generationcited by 15
  2. 2022Improving fairness in speaker verification via Group-adapted Fusion Networkcited by 11
  3. 2024The Generation Gap: Exploring Age Bias in the Value Systems of Large Language Modelscited by 5
  4. 2024Evaluating Large Language Models with fmevalcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 17.

20 papers.

Sort:

By area:

  1. 2026Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communitiescited by 4
  2. 2026Human Values in a Single Sentence: Moral Presence, Hierarchies, and Transformer Ensembles on the Schwartz Continuumcited by 3
  3. 2026Do Schwartz Higher-Order Values Help Sentence-Level Human Value Detection? A Study of Hierarchical Gating and Calibrationcited by 3
  4. 2025Who Gets the Kidney? Human-AI Alignment, Indecision, and Moral Valuescited by 2
  5. 2026What Does the AI Doctor Value? Auditing Pluralism in the Clinical Ethics of Language Modelscited by 2
  6. 2026The Judgment-Consequence Gap: LLM Moral Reasoning in Healthcare Decisionscited by 2
  7. 2025Classical AI vs. LLMs for Decision-Maker Alignment in Health Insurance Choicescited by 1
  8. 2025Designing Beyond Language: Sociotechnical Barriers in AI Health Technologies for Limited English Proficiencycited by 1
  9. 2026Overton Pluralistic Reinforcement Learning for Large Language Modelscited by 1
  10. 2026Affective Context Amplifies Sycophancy in LLM Responsescited by 1
  11. 2026Can Large Language Models Make Everyone Happy?cited by 0
  12. 2026Are Aligned Large Language Models Still Misaligned?cited by 0
8 more
  1. 2026Intra-Fairness Dynamics: The Bias Spillover Effect in Targeted LLM Alignmentcited by 0
  2. 2026Towards Cross-lingual Values Judgment: A Consensus-Pluralism Perspectivecited by 0
  3. 2026Slurry-as-a-Service: A Modest Proposal on Scalable Pluralistic Alignment for Nutrient Optimizationcited by 0
  4. 2026Event-Centric Human Value Understanding in News-Domain Texts: An Actor-Conditioned, Multi-Granularity Benchmarkcited by 0
  5. 2026Unweighted ranking for value-based decision making with uncertaintycited by 0
  6. 2026What Do People Actually Want From AI? Mapping Preference Pluralitycited by 0
  7. 2026MAVEN: A Macro-Societal Value Evaluation Framework of Multimodal Content with Compact Aligned Evaluatorscited by 0
  8. 2026ContextAdapt: Evaluating Contextual Adaptation and Value Alignment in LLMscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Toward a Theory of Value in AI Alignment
  2. 2025Evaluating AI Alignment in LLMs: Output Analysis of Value Priorities Across 75 Models with Human Benchmarking
  3. 2025Cultural Bias in Large Language Models: Evaluating AI Agents through Moral Questionnaires
  4. 2024Position: Towards Bidirectional Human-AI Alignment
  5. 2023A Multi-Level Framework for the AI Alignment Problem
  6. 2025Diverse Human Value Alignment for Large Language Models via Ethical Reasoning
  7. 2024A Moral Imperative: The Need for Continual Superalignment of Large Language Models
  8. 2020Aligning AI With Shared Human Values