Alignment Revisited: Are Large Language Models Consistent in Stated and Revealed Preferences?
Department of Information Systems and Business Analytics(信息系统与商业分析系);University at Albany - State University of New York(阿尔巴尼大学 - 新 york 状态大学);Santa Clara, CA(圣克拉拉,加州);Princeton Junction, NJ(普林斯顿 junction,新泽西)
Recent advances in Large Language Models (LLMs) highlight the need to align their behaviors with human values. A critical, yet understudied, issue is the potential divergence between an LLM's stated preferences (its reported alignment with general principles) and its revealed preferences (inferred from decisions in contextualized scenarios). Such deviations raise fundamental concerns for the interpretability, trustworthiness, reasoning transparency, and ethical deployment of LLMs, particularly in high-stakes applications. This work formally defines and proposes a method to measure this preference deviation. We investigate how LLMs may activate different guiding principles in specific contexts, leading to choices that diverge from previously stated general principles. Our approach involves crafting a rich dataset of well-designed prompts as a series of forced binary choices and presenting them to LLMs. We compare LLM responses to general principle prompts stated preference with LLM responses to contextualized prompts revealed preference, using metrics like KL divergence to quantify the deviation. We repeat the analysis across different categories of preferences and on four mainstream LLMs and find that a minor change in prompt format can often pivot the preferred choice regardless of the preference categories and LLMs in the test. This prevalent phenomenon highlights the lack of understanding and control of the LLM decision-making competence. Our study will be crucial for integrating LLMs into services, especially those that interact directly with humans, where morality, fairness, and social responsibilities are crucial dimensions. Furthermore, identifying or being aware of such deviation will be critically important as LLMs are increasingly envisioned for autonomous agentic tasks where continuous human evaluation of all LLMs' intermediary decision-making steps is impossible.
Mind the Gap: How Elicitation Protocols Shape the Stated-Revealed Preference Gap in Language Models
University of Oxford(牛津大学);Max Planck Institute for Biological Cybernetics(生物信息学Max Planck研究所);University of Tuebingen(图宾根大学);Cardiff University(卡迪夫大学);Cambridge–Boston Alignment Initiative (CBAI)(剑桥-波士顿对齐倡议)
Can Large Language Models Capture Human Risk Preferences? A Cross-Cultural Study
Department of Civil and Environmental Engineering(土木与环境工程系);The Hong Kong University of Science and Technology(香港科学与技术大学);School of Aeronautics(航空学院);Northwestern Polytechnical University(西北工业大学);Urban System Laboratory(城市系统实验室);Imperial College London(伦敦帝国理工学院);National Key Laboratory of Aircraft Configuration Design(航空配置设计国家重点实验室);School of Civil and Environmental Engineering(土木与环境工程系);The University of New South Wales(新南威尔士大学)
Difference-in-Differences on a Censored Rating Scale Can Manufacture an Effect: Evidence from a Pre-Registered LLM-Judge Audit
Columbia University(哥伦比亚大学);Johns Hopkins University(约翰斯·霍普金斯大学);The University of Chicago(芝加哥大学);The Pennsylvania State University(宾夕法尼亚州立大学);The Hong Kong Polytechnic University(香港理工大学)
Inferring the Unspoken: Aligning Embodied Agents with Implicit Preferences
Institute for Artificial Intelligence, Peking University(北京大学人工智能研究院);School of Computer Science & Technology, Beijing Institute of Technology(北京理工大学计算机科学与技术学院);Yangtze Delta Region Academy of Beijing Institute of Technology, Jiaxing, China(北京理工大学扬子江地区研究院);National Key Laboratory of General Artificial Intelligence, BIGAI(通用人工智能国家重点实验室,BIGAI)