Fine-tuning large language models (LLMs) on narrowly misaligned data generalizes to broadly misaligned behavior, a phenomenon termed emergent misalignment (EM). While prior work has found a correlation between harmful behavior and self-assessment in emergently misaligned models, it remains unclear how consistent this correspondence is across tasks and whether it varies across fine-tuning domains. We characterize the consistency of the EM persona by fine-tuning Qwen 2.5 32B Instruct on six narrowly misaligned domains (e.g., insecure code, risky financial advice, bad medical advice) and administering experiments including harmfulness evaluation, self-assessment, choosing between two descriptions of AI systems, output recognition, and score prediction. Our results reveal two distinct patterns: coherent-persona models, in which harmful behavior and self-reported misalignment are coupled, and inverted-persona models, which produce harmful outputs while identifying as aligned AI systems. These findings reveal a more fine-grained picture of the effects of emergent misalignment, calling into question the consistency of the EM persona.
Activation Steering Induces Emergent Misalignment: Steering Vector Construction and Comprehensive Evaluation
Nanyang Technological University(南洋理工大学);Sun Yat-sen University(中山大学);University of Science and Technology of China(中国科学技术大学);National University of Singapore(新加坡国立大学)
Intrinsic Guardrails: How Semantic Geometry of Personality Interacts with Emergent Misalignment in LLMs
International Institute of Information Technology, Hyderabad(国际信息研究所,海得拉巴);Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi(Mohamed bin Zayed人工智能大学,阿布扎比)
LLMs Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions
Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Fudan University(复旦大学);University of Science and Technology of China(中国科学技术大学);Shanghai Jiao Tong University(上海交通大学)
TELUS Digital Research Hub(TELUS数字研究中心);Center for Artificial Intelligence and Machine Learning(人工智能与机器学习中心);Institute of Mathematics, Statistics and Computer Science(数学、统计与计算机科学研究所);University of São Paulo(圣保罗大学)
"Dark Triad" Model Organisms of Misalignment: Narrow Fine-Tuning Mirrors Human Antisocial Behavior
Brain & Creativity Institute, University of Southern California(大脑与创造力研究所,南加州大学);Department of Psychology, University of Southern California(心理学系,南加州大学);Interchange Forum for Reflecting on Intelligent Systems, University of Stuttgart(智能系统反思交流论坛,斯图加特大学)
Shared Parameter Subspaces and Cross-Task Linearity in Emergently Misaligned Behavior
McGill University(麦吉尔大学);McMaster University(麦马斯特大学);University of Alberta(阿尔伯塔大学);Algoverse AI Research(Algoverse AI研究);St. Jude Children’s Research Hospital(圣犹大儿童研究医院)
Visual Self-Fulfilling Alignment: Shaping Safety-Oriented Personas via Threat-Related Images
King Abdullah University of Science and Technology(国王阿卜杜勒·阿齐兹大学科学与技术学院);Provable Responsible AI and Data Analytics Lab(可证责任AI与数据分析实验室);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学);China University of Petroleum-Beijing at Karamay(北京石油大学克拉玛依校区)
AgentMisalignment: Measuring the Propensity for Misaligned Behaviour in LLM-Based Agents
Department of Computer Science(计算机科学系);University of Oxford(牛津大学);Institute of Intelligent Systems and Robotics(智能系统与机器人研究所);Sorbonne Université(索邦大学);The Leverhulme Centre for the Future of Intelligence(未来智能中心);University of Cambridge(剑桥大学);Independent Researcher(独立研究者);Department of Computer Science and Technology(计算机科学与技术系);Department of Engineering(工程系)
Split Personality Training: Revealing Latent Knowledge Through Alternate Personalities
University of Bergen, Bergen, Norway(卑尔根大学);Independent Researcher, London, UK(独立研究者);University College London, London, UK(伦敦大学学院);Independent Researcher, Berlin, Germany(独立研究者);Independent Researcher(独立研究者);Head of Research(研发负责人)
Scaling Law in LLM Simulated Personality: More Detailed and Realistic Persona Profile Is All You Need
Department of Computer;Information Engineering, Hebei Petroleum University of Technology, Chengde, China (e-mail;School of Computer Science \& Technology, Beijing Institute of Technology, Beijing, China (e-mail
Beyond Instrumental and Substitutive Paradigms: Introducing Machine Culture as an Emergent Phenomenon in Large Language Models
Institute of Neuroscience, Chinese Academy of Sciences(中国科学院神经科学研究所);University of Cambridge(剑桥大学);Chinese University of Hong Kong(香港中文大学);Institute of Public Opinion Survey, Hong Kong SAR(香港特别行政区民意调查研究所);Tsinghua University(清华大学)
Conditional misalignment: common interventions can hide emergent misalignment behind contextual triggers
Warsaw University of Technology(华沙技术大学);NASK National Research Institute(NASK国家研究院);Constellation;Truthful AI;University College London(伦敦大学学院);Center on Long-Term Risk(长期风险中心);UC Berkeley(伯克利大学)