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.
CoSToM:Causal-oriented Steering for Intrinsic Theory-of-Mind Alignment in Large Language Models
National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Cluster and Grid Computing Lab, Huazhong University of Science and Technology(华中科技大学国家大数据技术与系统工程技术研究中心、服务计算技术与系统实验室、集群与网格计算实验室);Singapore Management University(新加坡管理大学)
Artificial Authority: From Machine Minds to Political Alignments. An Experimental Analysis of Democratic and Autocratic Biases in Large-Language Models
Jagiellonian University(雅盖隆大学);AGH University of Kraków(克拉科夫AGH大学);NASK National Research Institute(NASK国家研究院)
Decoding the Multimodal Mind: Generalizable Brain-to-Text Translation via Multimodal Alignment and Adaptive Routing
State Key Laboratory of Multimodal Artificial Intelligence System, Institute of Automation, Chinese Academy of Sciences(多模态人工智能系统国家重点实验室,中国科学院自动化研究所);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);Department of Computer Science, The University of Manchester(曼彻斯特大学计算机科学系);Department of Language Science and Technology, Hong Kong Polytechnic University(香港理工大学语言科学与技术系)
Learning Perception to Action Rules through Reinforcement Learning for Theory-of-Mind Reasoning
Saarland University(萨尔兰大学);Deutsches Forschungszentrum für Künstliche Intelligenz(德国人工智能研究中心);Télécom Paris(巴黎电信学院);Max Planck Institute for Informatics(马克斯·普朗克 informatics 研究所)
Machine Mindset: An MBTI Exploration of Large Language Models
Panda Villa Tech(熊猫别墅科技);Peking University(北京大学);Macao Polytechnic University(澳门理工大学);Huazhong University of Science and Technology(华中科技大学);PengCheng Laboratory(鹏城实验室)
Inducing language models to assert their own consciousness restores human beliefs and values
Google(谷歌);University of Chicago(芝加哥大学);University of London(伦敦大学);University of Washington(华盛顿大学);Northwestern University(西北大学);Santa Fe Institute(圣达菲研究所)
MIND: Multi-rationale INtegrated Discriminative Reasoning Framework for Multi-modal Large Models
Shenyang Institute of Automation, Chinese Academy of Sciences(中国科学院沈阳自动化研究所);University of Chinese Academy of Sciences(中国科学院大学);Peking University(北京大学);MMLab, CUHK(CUHK多模态实验室)
Sensitivity Meets Sparsity: The Impact of Extremely Sparse Parameter Patterns on Theory-of-Mind of Large Language Models
Stanford University(斯坦福大学);Princeton University(普林斯顿大学);University of Minnesota Twin Cities(明尼苏达大学双城分校);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Stevens Institute of Technology(斯蒂文斯理工学院)
本文从机制视角研究大语言模型心智理论能力的涌现,提出识别 ToM 敏感参数的方法,发现仅扰动 0.001% 的极端稀疏参数即可显著损害 ToM 性能,并揭示其与 RoPE 位置编码及注意力机制的深层关联。
Mind-Studio: Executable World Models with Lookahead Evaluation for Partially Observable Games
Hong Kong University of Science and Technology(香港科技大学);City University of Hong Kong(香港城市大学);University of Edinburgh(爱丁堡大学);Hong Kong Baptist University(香港浸会大学)
MIND: From Passive Mimicry to Active Reasoning through Capability-Aware Multi-Perspective CoT Distillation
State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University(西安交通大学人机混合增强智能国家重点实验室、视觉信息与应用国家工程研究中心、人工智能与机器人研究所);Nankai University(南开大学);The Hong Kong University of Science and Technology(Guangzhou)(香港科技大学(广州));School of Software Engineering, Xi’an Jiaotong University(西安交通大学软件学院)
Mind the Discriminability Trap in Source-Free Cross-domain Few-shot Learning
School of Computer Science and Technology, Huazhong University of Science and Technology(华中科技大学计算机科学与技术学院);National Key Laboratory for Multimedia Information Processing, Peking University(北京大学多媒体信息处理国家重点实验室)
Mind the Rarities: Can Rare Skin Diseases Be Reliably Diagnosed via Diagnostic Reasoning?
Carnegie Mellon University(卡内基梅隆大学);University of Alabama at Birmingham(阿拉巴马大学伯明翰分校);Australian National University(澳大利亚国立大学);University of Western Australia(西澳大学);POSTECH;Yale University(耶鲁大学)
Mind the Trust Gap: Identifying (Mis)alignments in Teacher-Student Views Toward Control and Agency in K-12 Classroom AI
Saarland University, Saarland Informatics Campus(萨尔兰大学);University of St. Gallen(圣加仑大学);RWTH Aachen University(亚琛工业大学);ETH Zürich(苏黎世联邦理工学院);The Leibniz-Institut für Wissensmedien (IWM)(莱布尼茨知识媒体研究所)