AI人格会成长吗?分析并基准化LLM代理在生活事件后的人格演变
原标题:Do AI Personas Grow? Analyzing and Benchmarking Personality Evolution in LLM Agents After Life Events
AI 摘要
该研究分析了基于人格条件的大语言模型代理(PC-Agents)在经历11种重大生活事件后的人格演变,使用大五人格特质作为心理测量锚点。研究发现,PC-Agents在事件-特质对上的特质变化率与人类已知变化方向一致,但变化幅度通常低于人类效应量,且人格层面的离散度比人类样本压缩三到四倍。研究引入了可复用的基准BFI-Adapt,用于评分事件诱发人格变化的方向保真度,并对14个模型进行了排名。结果表明,当前PC-Agents能模拟人类人格动态的平均值,但无法模拟其分布形态。
正文节选
Computer Science > Computation and Language Title:Do AI Personas Grow? Analyzing and Benchmarking Personality Evolution in LLM Agents After Life Events View PDF Abstract:Personality-conditioned LLM agents (PC-Agents) are increasingly used in emotional support, social simulation, and role-playing, motivating the development of lifelong agents that remain coherent over extended interactions. A key component of such coherence is personality evolution: agents should undergo plausible, ps