Exploring the Limits of LLMs in Simulating Partisan Polarization with Confirmation Bias Prompts

In this study, we investigate the potential of large language models (LLMs) to simulate partisan political polarization through conversation experiments. While previous research has demonstrated that LLM agents fail to reproduce human-like partisan polarization due to their inherent biases, we hypot...

Full description

Bibliographic Details

Main Authors:	Masashi Sakurai, Kento Ueta, Yasuhiro Hashimoto
Format:	Artigo
Language:	Inglês
Published:	MDPI AG 2025-08-01
Series:	Engineering Proceedings
Subjects:	large language models partisan polarization confirmation bias prompt engineering agent simulation
Online Access:	https://www.mdpi.com/2673-4591/107/1/2
Tags:	Add Tag No Tags, Be the first to tag this record!