The Chameleon's Limit: Investigating Persona Collapse and Homogenization in Large Language Models

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Xiao, Yunze, Zhang, Vivienne J., Yang, Chenghao, Ma, Ningshan, Xuan, Weihao, Huang, Jen-tse
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910170301333504
author Xiao, Yunze
Zhang, Vivienne J.
Yang, Chenghao
Ma, Ningshan
Xuan, Weihao
Huang, Jen-tse
author_facet Xiao, Yunze
Zhang, Vivienne J.
Yang, Chenghao
Ma, Ningshan
Xuan, Weihao
Huang, Jen-tse
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_24698
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle The Chameleon's Limit: Investigating Persona Collapse and Homogenization in Large Language Models
Xiao, Yunze
Zhang, Vivienne J.
Yang, Chenghao
Ma, Ningshan
Xuan, Weihao
Huang, Jen-tse
Computation and Language
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.
title The Chameleon's Limit: Investigating Persona Collapse and Homogenization in Large Language Models
topic Computation and Language
url https://arxiv.org/abs/2604.24698