Large language models (LLMs) can influence user trust and decision-making through subtle linguistic cues, yet the behavioral effects of manipulative outputs remain poorly quantified. We introduce a behavioral computing framework for measuring \textit{behavioral vulnerability}, defined as users' susceptibility to manipulative AI responses. Building on DarkPatterns-LLM benchmark, we generate controlled manipulative stimuli using Manipulation Gradient Descent (MGD), targeting biases associated with authority, urgency, and social proof. We analyze participant responses using the Multi-Stakeholder Impact Assessment Network (MSIAN) to model cross-user influence and the Temporal Harm Propagation Model (THPM) to characterize the persistence of behavioral effects over time. In a study involving 120 participants, manipulative framing produced significant changes in trust calibration and compliance ($p < 0.01$), with effects also propagating across social contexts. These findings highlight the need to extend LLM safety evaluation beyond model outputs to measurable behavioral consequences and provide a computational framework for quantifying individual, social, and temporal risks arising from manipulative AI interactions.
Measuring the Behavioral Fidelity of Long-Horizon Human Activity Simulations
Human-Computer Interaction Institute, School of Computer Science, Carnegie Mellon University(卡内基梅隆大学计算机科学学院人机交互研究所);Fujitsu Ltd.(富士通有限公司);Fujitsu Research of America(富士通美国研究院)
Measuring Reasoning Quality in LLMs: A Multi-Dimensional Behavioral Framework
Department of Computer Engineering, Tarsus University(塔鲁斯大学计算机工程系);School of Computing and Augmented Intelligence (SCAI), Arizona State University (ASU)(计算与增强智能学院(SCAI),亚利桑那州立大学(ASU));HumaConn AI Consulting(HumaConn AI咨询)
ETH Zürich(苏黎世联邦理工学院);ELLIS Institute Tübingen(图宾根ELLIS研究所);Max Planck Institute for Intelligent Systems(智能系统马克斯·普朗克研究院);Tübingen AI Center(图宾根人工智能中心);University of Toronto & Vector Institute(多伦多大学及向量研究所);EuroSafeAI(欧洲安全人工智能)
Leveraging LLMs for Predictive Insights in Food Policy and Behavioral Interventions
El-Erian Institute(埃尔-埃里安研究所);Cambridge Judge Business School(剑桥贾奇商学院);University of Cambridge(剑桥大学);YNOT Institute(YNOT研究所);Queen’s College, Cambridge(剑桥大学王后学院);Apple(苹果公司);Harvard Law School(哈佛法学院);Harvard University(哈佛大学)
CUTE: Measuring LLMs' Understanding of Their Tokens
Center for Information and Language Processing, LMU Munich(慕尼黑大学信息与语言处理中心);Munich Center for Machine Learning(慕尼黑机器学习中心);School of Computation, Information and Technology, TU Munich(慕尼黑工业大学计算、信息与技术学院);Munich Data Science Institute(慕尼黑数据科学研究所)
Faculty of Data and Decision Sciences, Technion(以色列理工学院数据与决策科学学院);The Hebrew University of Jerusalem(耶路撒冷希伯来大学);Google Research(谷歌研究院);Hebrew University Business School(希伯来大学商学院);Federmann Center for the Study of Rationality, Hebrew University(希伯来大学费德曼理性研究中心);Department of Cognitive and Brain Sciences, Hebrew University(希伯来大学认知与脑科学系)
Choose Your Game Wisely: Measuring Game-Theoretic Structures in Real-World Vehicle Interactions
School of Automation and Intelligent Sensing, Shanghai Jiao Tong University(上海交通大学自动化与智能感知学院);School of Airspace Science and Engineering, Shandong University(山东大学空天科学与工程学院);Global Institute of Future Technology, Shanghai Jiao Tong University(上海交通大学未来技术全球研究院);Global College, Shanghai Jiao Tong University(上海交通大学全球学院)
Advancing Methodology for Social Science Research Using Alternate Reality Games: Proof-of-Concept Through Measuring Individual Differences and Adaptability and their impact on Team Performance