研究大模型人格特质如何随温度变化而显现，发现架构影响性格稳定性。
Decoding Emergent Big Five Traits in Large Language Models: Temperature-Dependent Expression and Architectural Clustering
- 用人格五因素框架测试六款大模型，分析采样温度对性格表现的影响。
- 神经质和外向性随温度升高显著变化，其他维度相对稳定。
- 模型按架构聚类，提示结构设计决定性格表达的稳定性，适合伦理治理参考。
随着大语言模型在以人为本的应用中日益重要，理解其类人格行为对于负责任地开发与部署至关重要。本文系统评估了六款大语言模型，采用五因素人格量表-2（BFI-2）框架，考察在不同采样温度下的特质表现。结果显示，五个维度中有四个存在显著差异，其中神经质和外向性对温度调整尤为敏感。进一步的层次聚类揭示了不同的模型集群，表明架构特征可能使某些模型更倾向于稳定的特质表现。这些结果为大模型中类人格模式的涌现提供了新见解，并为模型调优、选择及人工智能伦理治理提供了新视角。数据与代码已公开：https://osf.io/bsvzc/?view_only=6672219bede24b4e875097426dc3fac1
原文摘要 · Abstract (English)
As Large Language Models (LLMs) become integral to human-centered applications, understanding their personality-like behaviors is increasingly important for responsible development and deployment. This paper systematically evaluates six LLMs, applying the Big Five Inventory-2 (BFI-2) framework, to assess trait expressions under varying sampling temperatures. We find significant differences across four of the five personality dimensions, with Neuroticism and Extraversion susceptible to temperature adjustments. Further, hierarchical clustering reveals distinct model clusters, suggesting that architectural features may predispose certain models toward stable trait profiles. Taken together, these results offer new insights into the emergence of personality-like patterns in LLMs and provide a new perspective on model tuning, selection, and the ethical governance of AI systems. We share the data and code for this analysis here: https://osf.io/bsvzc/?view_only=6672219bede24b4e875097426dc3fac1
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。