随着大型语言模型（LLM）日益融入日常工作流程，用户会通过多轮协作塑造结果，一个关键问题随之出现：具有不同人格特质的用户是否会系统性地偏好某些 LLM 而非其他模型？我们开展了一项研究，32 名参与者均匀分布于四种 Keirsey 人格类型，评估他们在数据分析、创意写作、信息检索和写作辅助四项协作任务中与 GPT-4 和 Claude 3.5 的交互。结果揭示了显著的人格驱动偏好：Rationals 强烈偏好 GPT-4，尤其是在目标导向任务中；而 Idealists 偏爱 Claude 3.5，特别是在创意和分析任务中。其他人格类型表现出依赖任务的偏好。对定性反馈的情感分析证实了这些模式。值得注意的是，各模型的总体有用性评分相近，表明基于人格的分析能够揭示传统评估所遗漏的 LLM 差异。
英文摘要：
As Large Language Models (LLMs) increasingly integrate into everyday workflows, where users shape outcomes through multi-turn collaboration, a critical question emerges: do users with different personality traits systematically prefer certain LLMs over others? We conducted a study with 32 participants evenly distributed across four Keirsey personality types, evaluating their interactions with GPT-4 and Claude 3.5 across four collaborative tasks: data analysis, creative writing, information retrieval, and writing assistance. Results revealed significant personality-driven preferences: Rationals strongly preferred GPT-4, particularly for goal-oriented tasks, while idealists favored Claude 3.5, especially for creative and analytical tasks. Other personality types showed task-dependent preferences. Sentiment analysis of qualitative feedback confirmed these patterns. Notably, aggregate helpfulness ratings were similar across models, showing how personality-based analysis reveals LLM differences that traditional evaluations miss.
Exploring the Impact of Personality Traits on Conversational Recommender Systems: A Simulation with Large Language Models
Chinese University of Hong Kong（香港中文大学）；National University of Singapore（新加坡国立大学）；Singapore Management University（新加坡管理大学）；Hong Kong Baptist University（香港浸会大学）；Huazhong University of Science and Technology（华中科技大学）
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）
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）
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）
Augmenting Dialog with Think-Aloud Utterances for Modeling Individual Personality Traits by LLM
Institute of Science Tokyo（东京科学大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Nara Institute of Science and Technology（奈良先端科学技术大学院大学）；Fujitsu Limited（富士通株式会社）
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）
Activation-Space Personality Steering: Hybrid Layer Selection for Stable Trait Control in LLMs
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, The University of Western Australia（西澳大学物理数学与计算学院）；School of Psychological Science, The University of Western Australia（西澳大学心理学科学学院）；School of Computing, Macquarie University（麦考瑞大学计算机学院）
