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

arXiv: https://arxiv.org/abs/2409.09586 · HTML: https://mlsanity.com/paper/2409.09586/

## Key facts

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

## Placed in

- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)

## Builds on (most cited first, 18 of 18)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Improving fairness in machine learning systems: What do industry practitioners need?](https://mlsanity.com/paper/1812.05239/) (2018)
- [DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection](https://mlsanity.com/paper/2001.00179/) (2020)
- [A Roadmap to Pluralistic Alignment](https://mlsanity.com/paper/2402.05070/) (2024)
- [Moral Foundations of Large Language Models](https://mlsanity.com/paper/2310.15337/) (2023)
- [Interpretable Deep Learning under Fire](https://mlsanity.com/paper/1812.00891/) (2018)
- [Moral Mimicry: Large Language Models Produce Moral Rationalizations Tailored to Political Identity](https://mlsanity.com/paper/2209.12106/) (2022)
- [Diminished Diversity-of-Thought in a Standard Large Language Model](https://mlsanity.com/paper/2302.07267/) (2023)
- [Deepfakes, Phrenology, Surveillance, and More! A Taxonomy of AI Privacy Risks](https://mlsanity.com/paper/2310.07879/) (2023)
- [Farsight: Fostering Responsible AI Awareness During AI Application Prototyping](https://mlsanity.com/paper/2402.15350/) (2024)
- [Geographical Erasure in Language Generation](https://mlsanity.com/paper/2310.14777/) (2023)
- [Improving fairness in speaker verification via Group-adapted Fusion Network](https://mlsanity.com/paper/2202.11323/) (2022)
- [The Generation Gap: Exploring Age Bias in the Value Systems of Large Language Models](https://mlsanity.com/paper/2404.08760/) (2024)
- [Measuring Value Alignment](https://mlsanity.com/paper/2312.15241/) (2023)
- [Evaluating Large Language Models with fmeval](https://mlsanity.com/paper/2407.12872/) (2024)

## Built on by (most cited first, 20 of 20)

- [Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communities](https://mlsanity.com/paper/2604.05339/) (2026)
- [Human Values in a Single Sentence: Moral Presence, Hierarchies, and Transformer Ensembles on the Schwartz Continuum](https://mlsanity.com/paper/2601.14172/) (2026)
- [Do Schwartz Higher-Order Values Help Sentence-Level Human Value Detection? A Study of Hierarchical Gating and Calibration](https://mlsanity.com/paper/2602.00913/) (2026)
- [The Judgment-Consequence Gap: LLM Moral Reasoning in Healthcare Decisions](https://mlsanity.com/paper/2608.05583/) (2026)
- [Affective Context Amplifies Sycophancy in LLM Responses](https://mlsanity.com/paper/2608.21242/) (2026)
- [Who Gets the Kidney? Human-AI Alignment, Indecision, and Moral Values](https://mlsanity.com/paper/2506.00079/) (2025)
- [What Does the AI Doctor Value? Auditing Pluralism in the Clinical Ethics of Language Models](https://mlsanity.com/paper/2605.18738/) (2026)
- [Classical AI vs. LLMs for Decision-Maker Alignment in Health Insurance Choices](https://mlsanity.com/paper/2510.06093/) (2025)
- [Designing Beyond Language: Sociotechnical Barriers in AI Health Technologies for Limited English Proficiency](https://mlsanity.com/paper/2511.07277/) (2025)
- [Intra-Fairness Dynamics: The Bias Spillover Effect in Targeted LLM Alignment](https://mlsanity.com/paper/2602.16438/) (2026)
- [Overton Pluralistic Reinforcement Learning for Large Language Models](https://mlsanity.com/paper/2602.20759/) (2026)
- [Can Large Language Models Make Everyone Happy?](https://mlsanity.com/paper/2602.11091/) (2026)
- [Are Aligned Large Language Models Still Misaligned?](https://mlsanity.com/paper/2602.11305/) (2026)
- [Towards Cross-lingual Values Judgment: A Consensus-Pluralism Perspective](https://mlsanity.com/paper/2602.17283/) (2026)
- [Slurry-as-a-Service: A Modest Proposal on Scalable Pluralistic Alignment for Nutrient Optimization](https://mlsanity.com/paper/2603.02420/) (2026)
- [Event-Centric Human Value Understanding in News-Domain Texts: An Actor-Conditioned, Multi-Granularity Benchmark](https://mlsanity.com/paper/2603.17838/) (2026)
- [Unweighted ranking for value-based decision making with uncertainty](https://mlsanity.com/paper/2605.13601/) (2026)
- [What Do People Actually Want From AI? Mapping Preference Plurality](https://mlsanity.com/paper/2606.06674/) (2026)
- [MAVEN: A Macro-Societal Value Evaluation Framework of Multimodal Content with Compact Aligned Evaluators](https://mlsanity.com/paper/2608.18096/) (2026)
- [ContextAdapt: Evaluating Contextual Adaptation and Value Alignment in LLMs](https://mlsanity.com/paper/2609.38260/) (2026)

## 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.