Chameleon的极限：探究大型语言模型中的人格崩溃与同质化
The Chameleon's Limit: Investigating Persona Collapse and Homogenization in Large Language Models
AI总结：
研究发现大型语言模型中存在人格崩溃现象，导致代理行为模式趋同。通过提出覆盖度、均匀度和复杂度指标，揭示模型在不同维度和领域的人格表现差异，并释放工具支持群体评估。
摘要：
基于大型语言模型（LLMs）的应用，如多智能体模拟，需要代理群体的多样性。我们识别出一种普遍的失败模式，称为人格崩溃：即使每个代理有独特的配置，它们仍会收敛到狭窄的行为模式，产生同质化的模拟群体。为量化人格崩溃，我们提出一个框架，衡量群体占据的人格空间（覆盖度）、代理在空间中的分布均匀性（均匀度）以及由此产生的行为模式的丰富性（复杂度）。在十种LLM上评估人格模拟（BFI-44）、道德推理和自我介绍任务时，我们观察到人格崩溃在两个轴上：（1）维度：模型在某一轴上可能表现多样，但在另一轴上结构上退化；（2）领域：同一模型可能在人格方面崩溃最严重，但在道德推理方面却最多样。进一步的项目级诊断揭示，行为变化追踪粗粒度的人口统计数据，而非每个角色中指定的细粒度个体差异。反直觉的是，实现最高每人格保真度的模型通常产生最刻板的群体。我们释放我们的工具包和数据以支持LLM的群体级评估。
英文摘要：
Applications based on large language models (LLMs), such as multi-agent simulations, require population diversity among agents. We identify a pervasive failure mode we term \emph{Persona Collapse}: agents each assigned a distinct profile nonetheless converge into a narrow behavioral mode, producing a homogeneous simulated population. To quantify persona collapse, we propose a framework that measures how much of the persona space a population occupies (Coverage), how evenly agents spread across it (Uniformity), and how rich the resulting behavioral patterns are (Complexity). Evaluating ten LLMs on personality simulation (BFI-44), moral reasoning, and self-introduction, we observe persona collapse along two axes: (1) Dimensions: a model can appear diverse on one axis yet structurally degenerate on another, and (2) Domains: the same model may collapse the most in personality yet be the most diverse in moral reasoning. Furthermore, item-level diagnostics reveal that behavioral variation tracks coarse demographic stereotypes rather than the fine-grained individual differences specified in each persona. Counter-intuitively, \textbf{the models achieving the highest per-persona fidelity consistently produce the most stereotyped populations}. We release our toolkit and data to support population-level evaluation of LLMs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
