Mind the Value-Action Gap: Do LLMs Act in Alignment with Their Values?
Hua Shen, Nicholas Clark, Tanu Mitra
Abstract
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.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Cited by top-tier papers8
- SimBench: Benchmarking the Ability of Large Language Models to Simulate Human BehaviorsTiancheng Hu, Joachim Baumann, Lorenzo Lupo, Nigel Collier et al.ICLR 2026 · 61 citations
- Distributive Fairness in Large Language Models: Evaluating Alignment with Human ValuesHadi Hosseini, Samarth KhannaNeurIPS 2025 · 14 citations
- The Siren Song of LLMs: How Users Perceive and Respond to Dark Patterns in Large Language ModelsYike Shi, Qing Xiao, Qing Hu, Hong Shen et al.CHI 2026 · 7 citations
- Deep Value Benchmark: Measuring Whether Models Generalize Deep Values or Shallow PreferencesJoshua Ashkinaze, Hua Shen, Sai Avula, Eric Gilbert et al.NeurIPS 2025 · 7 citations
- Whose Facts Win? LLM Source Preferences under Knowledge ConflictsJakob Schuster, Vagrant Gautam, Katja MarkertACL 2026 · 3 citations
Builds on7
- Human-AI Interaction in Human Resource Management: Understanding Why Employees Resist Algorithmic Evaluation at Workplaces and How to Mitigate BurdensHyanghee Park, Daehwan Ahn, Kartik Hosanagar, Joonhwan LeeCHI 2021 · 117 citations
- A Framework of Severity for Harmful Content OnlineMorgan Klaus Scheuerman, Jialun Aaron Jiang, Casey Fiesler, Jed R. BrubakerCSCW 2021 · 113 citations
- Designing Responsible AI: Adaptations of UX Practice to Meet Responsible AI ChallengesQiaosi Wang, Michael Madaio, Shaun K. Kane, Shivani Kapania et al.CHI 2023 · 90 citations
- ERASER: A Benchmark to Evaluate Rationalized NLP ModelsJay DeYoung, Sarthak Jain, Nazneen Fatema Rajani, Eric P. Lehman et al.ACL 2020 · 36 citations
- Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language ModelsPaul Röttger, Valentin Hofmann, Valentina Pyatkin, Musashi Hinck et al.ACL 2024
Related papers
- Unintended Harms of Value-Aligned LLMs: Psychological and Empirical InsightsSooyung Choi, Jaehyeok Lee, Xiaoyuan Yi, Jing Yao et al.ACL 2025
- ValueBench: Towards Comprehensively Evaluating Value Orientations and Understanding of Large Language ModelsYuanyi Ren, Haoran Ye, Hanjun Fang, Xin Zhang et al.ACL 2024
- Value Portrait: Assessing Language Models' Values through Psychometrically and Ecologically Valid ItemsJongwook Han, Dongmin Choi, Woojung Song, Eun-Ju Lee et al.ACL 2025
- Expectation Alignment of Language Models for Real-World User ExpectationsMiaomiao Li, Yang Wang, Bin Liang, Shudong Liu et al.ICML 2026
- LENS: Multi-level Evaluation of Multimodal Reasoning with Large Language ModelsRuilin Yao, Bo Zhang, Jirui Huang, Xinwei Long et al.ICLR 2026 · 8 citations
