Simulating Opinion Dynamics with Networks of LLM-based Agents

arXiv:2311.09618v2 Announce Type: replace-cross
Abstract: Accurately simulating human opinion dynamics is crucial for understanding a variety of societal phenomena, including polarization and the spread of misinformation. However, the agent-based models (ABMs) commonly used for such simulations often over-simplify human behavior. We propose a new approach to simulating opinion dynamics based on populations of Large Language Models (LLMs). Our findings reveal a strong inherent bias in LLM agents towards producing accurate information, leading simulated agents to consensus in line with scientific …

abstract agent agents arxiv behavior cs.cl dynamics human llm misinformation networks opinion physics.soc-ph simulations type understanding