Large language models (LLMs) have significantly advanced dialogue systems and role-playing agents through their ability to generate human-like text. While prior studies have shown that LLMs can exhibit distinct and consistent personalities, the mechanisms through which these models encode and express specific personality traits remain poorly understood. To address this, we investigate how various factors, such as cultural norms and environmental stressors, encoded within LLMs, shape their personality traits, guided by the theoretical framework of social determinism. Inspired by related work on LLM interpretability, we propose a training-free approach to modify the model's behavior by extracting and steering latent features corresponding to factors within the model, thereby eliminating the need for retraining. Furthermore, we analyze the implications of these factors for model safety, focusing on their impact through the lens of personality.
Do Personality Traits Interfere? Geometric Limitations of Steering in Large Language Models
Network Analysis and Social Influence Modelling (NASIM) Lab（网络分析与社会影响建模实验室）；School of Physics Maths and Computing（物理数学计算学院）；The University of Western Australia（西澳大学）；School of Computing（计算学院）；Macquarie University（麦觉瑞大学）
Predicting the Big Five Personality Traits in Chinese Counselling Dialogues Using Large Language Models
Zhejiang University（浙江大学）；School of Engineering, Westlake University（西湖大学工程学院）；Westlake University（西湖大学）；School of Early Childhood Education, Hangzhou Polytechnic（杭州职业技术学院幼儿教育学院）
Evaluating Personality Traits in Large Language Models: Insights from Psychological Questionnaires
School of Physics, Mathematics and Computing（物理、数学与计算学院）；University of Western Australia（西澳大学）；School of Computing（计算机学院）；School of Psychological Sciences（心理科学学院）
Neuron-based Personality Trait Induction in Large Language Models
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学首都人工智能学院）；Tongyi Lab（通义实验室）；Institute of Statistics and Big Data, Renmin University of China（中国人民大学统计与大数据研究院）
The Dark Patterns of Personalized Persuasion in Large Language Models: Exposing Persuasive Linguistic Features for Big Five Personality Traits in LLMs Responses
Warsaw University of Technology（华沙理工大学）；University of Warsaw（华沙大学）
Personality Vector: Modulating Personality of Large Language Models by Model Merging
Department of Human-Artificial Intelligence Interaction, Sungkyunkwan University（人类-人工智能交互系，成均馆大学）；Department of Immersive Media Engineering, Sungkyunkwan University（沉浸式媒体工程系，成均馆大学）
Beyond BFI: The CSI for Enhanced Reliability and Validity in Evaluating LLM Personality Traits
University of Illinois Chicago（伊利诺伊大学芝加哥分校）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Microsoft Research Asia（微软亚洲研究院）；North Carolina State University（北卡罗来纳州立大学）
