In many real-world applications, large language models (LLMs) operate as independent agents without interaction, thereby limiting coordination. In this setting, we examine how prompt framing influences decisions in a threshold voting task involving individual-group interest conflict. Two logically equivalent prompts with different framings were tested across diverse LLM families under isolated trials. Results show that prompt framing significantly influences choice distributions, often shifting preferences toward risk-averse options. Surface linguistic cues can even override logically equivalent formulations. This suggests that observed behavior reflects a tendency consistent with a preference for instrumental rather than cooperative rationality when success requires risk-bearing. The findings highlight framing effects as a significant bias source in non-interacting multi-agent LLM deployments, informing alignment and prompt design.
Auditing Framing-Sensitive Behavioral Instability in Large Language Models for Mental Health Interactions
a School of computer science, digital engineering and AI, Long Island University, Brooklyn, NY, USA(a 计算科学与数字工程及人工智能学院,罗格斯大学,布鲁克林,纽约,美国);b Department of Psychology, Long Island University, Brooklyn, NY, USA(b 心理学系,罗格斯大学,布鲁克林,纽约,美国)
The Invisible Editorial Layer: Formalizing Undisclosed Inference-Time Steering, Probability Placement, and the Attribution Problem in Deployed Language Models
The A-R Behavioral Space: Execution-Level Profiling of Tool-Using Language Model Agents in Organizational Deployment
Cardiff School of Technologies, Cardiff Metropolitan University(卡迪夫技术学院,卡迪夫市政大学);School of Professional Studies, Clark University(专业研究学院,克拉克大学);Harvard Medical School, Harvard University(哈佛医学院,哈佛大学)
Behind Harmful Compliance: Behavioral and Mechanistic Divergence Across LLM Jailbreaks
Department of Computer Science(计算机科学系);Luddy School of Informatics, Computing, and Engineering(信息学、计算与工程学院);Indiana University Bloomington(印第安纳大学布卢明顿分校)
REGARD: Regional Affective Differences in Large Language Models
Ivannikov Institute for System Programming of the Russian Academy of Sciences(俄罗斯科学院伊万尼科夫系统编程研究所);Russian Presidential Academy of National Economy and Public Administration(俄罗斯总统国民经济与公共管理学院)
GenPT: Beyond Self-Report for Reliable LLM Psychometrics via Generative Projective Testing
School of Computer Science and Engineering, Northeastern University(东北大学计算机科学与工程学院);School of Computing and Information Systems, Singapore Management University(新加坡管理学院计算机与信息学院);Mental Health Education Center, Northeastern University(东北大学心理健康教育中心);School of Psychology, Northeast Normal University(东北师范大学心理学系);Faculty of psychology, Southwest University(西南大学心理学系);School of Sociology and Psychology, Central University of Finance and Economics(中央财经大学社会学与心理学学院);College of Arts, Northeastern University(东北大学艺术学院)
No Usable Linear "Capitulation Direction" in Two Small LLMs: A Validation Protocol for Activation-Steering Claims, and a Cross-Family Behavioral Study of Sycophancy Under Pushback
Large Language Model-Powered Conversational Agent Delivering Problem-Solving Therapy (PST) for Family Caregivers: Enhancing Empathy and Therapeutic Alliance Using In-Context Learning
Florida State University(佛罗里达州立大学);University of Washington(华盛顿大学);University of Texas at Austin(德克萨斯大学奥斯汀分校)
Data Science Section, IT University of Copenhagen(丹麦哥本哈根IT大学数据科学系);Computer Science Department, University of Milan(意大利米兰大学计算机科学系);Copenhagen Center for Social Data Science, University of Copenhagen(丹麦哥本哈根大学哥本哈根社会科学数据科学中心)