Emergence of human-like polarization among large language model agents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Piao, Jinghua, Lu, Zhihong, Gao, Chen, Xu, Fengli, Hu, Qinghua, Santos, Fernando P., Li, Yong, Evans, James
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912384666304512
author Piao, Jinghua
Lu, Zhihong
Gao, Chen
Xu, Fengli
Hu, Qinghua
Santos, Fernando P.
Li, Yong
Evans, James
author_facet Piao, Jinghua
Lu, Zhihong
Gao, Chen
Xu, Fengli
Hu, Qinghua
Santos, Fernando P.
Li, Yong
Evans, James
contents Rapid advances in large language models (LLMs) have not only empowered autonomous agents to generate social networks, communicate, and form shared and diverging opinions on political issues, but have also begun to play a growing role in shaping human political deliberation. Our understanding of their collective behaviours and underlying mechanisms remains incomplete, however, posing unexpected risks to human society. In this paper, we simulate a networked system involving thousands of large language model agents, discovering their social interactions, guided through LLM conversation, result in human-like polarization. We discover that these agents spontaneously develop their own social network with human-like properties, including homophilic clustering, but also shape their collective opinions through mechanisms observed in the real world, including the echo chamber effect. Similarities between humans and LLM agents -- encompassing behaviours, mechanisms, and emergent phenomena -- raise concerns about their capacity to amplify societal polarization, but also hold the potential to serve as a valuable testbed for identifying plausible strategies to mitigate polarization and its consequences.
format Preprint
id arxiv_https___arxiv_org_abs_2501_05171
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Emergence of human-like polarization among large language model agents
Piao, Jinghua
Lu, Zhihong
Gao, Chen
Xu, Fengli
Hu, Qinghua
Santos, Fernando P.
Li, Yong
Evans, James
Social and Information Networks
Computers and Society
Rapid advances in large language models (LLMs) have not only empowered autonomous agents to generate social networks, communicate, and form shared and diverging opinions on political issues, but have also begun to play a growing role in shaping human political deliberation. Our understanding of their collective behaviours and underlying mechanisms remains incomplete, however, posing unexpected risks to human society. In this paper, we simulate a networked system involving thousands of large language model agents, discovering their social interactions, guided through LLM conversation, result in human-like polarization. We discover that these agents spontaneously develop their own social network with human-like properties, including homophilic clustering, but also shape their collective opinions through mechanisms observed in the real world, including the echo chamber effect. Similarities between humans and LLM agents -- encompassing behaviours, mechanisms, and emergent phenomena -- raise concerns about their capacity to amplify societal polarization, but also hold the potential to serve as a valuable testbed for identifying plausible strategies to mitigate polarization and its consequences.
title Emergence of human-like polarization among large language model agents
topic Social and Information Networks
Computers and Society
url https://arxiv.org/abs/2501.05171