# Mind the Value-Action Gap: Do LLMs Act in Alignment with Their Values?

arXiv: https://arxiv.org/abs/2501.15463 · HTML: https://mlsanity.com/paper/2501.15463/

## Key facts

- Cited by 51 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 51 references that are in the map.
- First posted on arXiv 26 Jan 2025.

## Builds on (most cited first, 17 of 17)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [Artificial Intelligence, Values and Alignment](https://mlsanity.com/paper/2001.09768/) (2020)
- [Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models](https://mlsanity.com/paper/2402.16786/) (2024)
- [Faithfulness vs. Plausibility: On the (Un)Reliability of Explanations from Large Language Models](https://mlsanity.com/paper/2402.04614/) (2024)
- [Interpretable Deep Learning under Fire](https://mlsanity.com/paper/1812.00891/) (2018)
- [How Well Do LLMs Represent Values Across Cultures? Empirical Analysis of LLM Responses Based on Hofstede Cultural Dimensions](https://mlsanity.com/paper/2406.14805/) (2024)
- [Gender, Race, and Intersectional Bias in Resume Screening via Language Model Retrieval](https://mlsanity.com/paper/2407.20371/) (2024)
- [Can Language Models Reason about Individualistic Human Values and Preferences?](https://mlsanity.com/paper/2410.03868/) (2024)
- [LLM-GLOBE: A Benchmark Evaluating the Cultural Values Embedded in LLM Output](https://mlsanity.com/paper/2411.06032/) (2024)
- ["They are uncultured": Unveiling Covert Harms and Social Threats in LLM Generated Conversations](https://mlsanity.com/paper/2405.05378/) (2024)
- [A Framework of Severity for Harmful Content Online](https://mlsanity.com/paper/2108.04401/) (2021)
- [Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testing](https://mlsanity.com/paper/2406.14230/) (2024)
- [Improving fairness in speaker verification via Group-adapted Fusion Network](https://mlsanity.com/paper/2202.11323/) (2022)
- [Risk and Response in Large Language Models: Evaluating Key Threat Categories](https://mlsanity.com/paper/2403.14988/) (2024)
- [Evaluating Large Language Models with fmeval](https://mlsanity.com/paper/2407.12872/) (2024)

## Built on by (most cited first, 30 of 51)

- [Actions Speak Louder than Words: Agent Decisions Reveal Implicit Biases in Language Models](https://mlsanity.com/paper/2501.17420/) (2025)
- [Whose Facts Win? LLM Source Preferences under Knowledge Conflicts](https://mlsanity.com/paper/2601.03746/) (2026)
- [Fluent but Foreign: Even Regional LLMs Lack Cultural Alignment](https://mlsanity.com/paper/2505.21548/) (2025)
- [Distributive Fairness in Large Language Models: Evaluating Alignment with Human Values](https://mlsanity.com/paper/2502.00313/) (2025)
- [Do Psychometric Tests Work for Large Language Models? Evaluation of Tests on Sexism, Racism, and Morality](https://mlsanity.com/paper/2510.11254/) (2025)
- [Knowing But Not Doing: Convergent Morality and Divergent Action in LLMs](https://mlsanity.com/paper/2601.07972/) (2026)
- [Evaluating Alignment of Behavioral Dispositions in LLMs](https://mlsanity.com/paper/2602.11328/) (2026)
- [Do Role-Playing Agents Practice What They Preach? Belief-Behavior Consistency in LLM-Based Simulations of Human Trust](https://mlsanity.com/paper/2507.02197/) (2025)
- [Deep Value Benchmark: Measuring Whether Models Generalize Deep Values or Shallow Preferences](https://mlsanity.com/paper/2511.02109/) (2025)
- [The Behavioral Fabric of LLM-Powered GUI Agents: Human Values and Interaction Outcomes](https://mlsanity.com/paper/2601.16356/) (2026)
- [ValueFlow: Measuring the Propagation of Value Perturbations in Multi-Agent LLM Systems](https://mlsanity.com/paper/2602.08567/) (2026)
- [Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communities](https://mlsanity.com/paper/2604.05339/) (2026)
- [Are Language Models Sensitive to Morally Irrelevant Distractors?](https://mlsanity.com/paper/2602.09416/) (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)
- [Human Psychometric Questionnaires Mischaracterize LLM Behavior](https://mlsanity.com/paper/2509.10078/) (2025)
- [From Passive to Persuasive: Localized Activation Injection for Empathy and Negotiation](https://mlsanity.com/paper/2511.12832/) (2025)
- [Can Finetuing LLMs on Small Human Samples Increase Heterogeneity, Alignment, and Belief-Action Coherence?](https://mlsanity.com/paper/2511.21218/) (2025)
- [Lessons Without Borders? Evaluating Cultural Alignment of LLMs Using Multilingual Story Moral Generation](https://mlsanity.com/paper/2604.08797/) (2026)
- [To Whom Do Language Models Align? Measuring Principal Hierarchies Under High-Stakes Competing Demands](https://mlsanity.com/paper/2605.12120/) (2026)
- [What Does the AI Doctor Value? Auditing Pluralism in the Clinical Ethics of Language Models](https://mlsanity.com/paper/2605.18738/) (2026)
- [ActTraitBench: Quantifying the Knowledge-Decision Gap in Large Language Models via Human-Grounded Behavioral Validation](https://mlsanity.com/paper/2605.29791/) (2026)
- [Free Lunch for User Experience: Crowdsourcing Agents for Scalable User Studies](https://mlsanity.com/paper/2505.22981/) (2025)
- [Value Alignment Tax: Measuring Value Trade-offs in LLM Alignment](https://mlsanity.com/paper/2602.12134/) (2026)
- [Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook](https://mlsanity.com/paper/2604.06210/) (2026)
- [Beyond Social Pressure: Benchmarking Epistemic Attack in Large Language Models](https://mlsanity.com/paper/2604.07749/) (2026)
- [Beyond Value Benchmarks: Measuring Value-Structure Alignment in Large Language Models via Symmetric Q-Sorts](https://mlsanity.com/paper/2606.21939/) (2026)
- [When Preferences Fail to Become Incentives: A Utility-Behavior Gap in Large Language Models](https://mlsanity.com/paper/2606.22974/) (2026)
- [PLURAL: A Global Dataset for Value Alignment](https://mlsanity.com/paper/2607.08034/) (2026)

## Abstract (arXiv)

Existing research primarily evaluates the values of LLMs by examining their stated inclinations towards specific values. However, the "Value-Action Gap," a phenomenon rooted in environmental and social psychology, reveals discrepancies between individuals' stated values and their actions in real-world contexts. To what extent do LLMs exhibit a similar gap between their stated values and their actions informed by those values? This study introduces ValueActionLens, an evaluation framework to assess the alignment between LLMs' stated values and their value-informed actions. The framework encompasses the generation of a dataset comprising 14.8k value-informed actions across twelve cultures and eleven social topics, and two tasks to evaluate how well LLMs' stated value inclinations and value-informed actions align across three different alignment measures. Extensive experiments reveal that the alignment between LLMs' stated values and actions is sub-optimal, varying significantly across scenarios and models. Analysis of misaligned results identifies potential harms from certain value-action gaps. To predict the value-action gaps, we also uncover that leveraging reasoned explanations improves performance. These findings underscore the risks of relying solely on the LLMs' stated values to predict their behaviors and emphasize the importance of context-aware evaluations of LLM values and value-action gaps.