Competing LLM Agents in a Non-Cooperative Game of Opinion Polarisation

TL;DR

This paper models opinion polarization using a game-theoretic approach with LLM agents, revealing how confirmation bias and resource strategies influence societal opinion dynamics and polarization levels.

Contribution

It introduces a novel non-cooperative game framework incorporating social psychology principles and resource constraints to analyze opinion formation and influence strategies.

Findings

Higher confirmation bias increases group polarization.

Lower confirmation bias leads to opinion fragmentation.

Resource-intensive debunking can have short-term benefits but risks long-term depletion.

Abstract

We introduce a novel non-cooperative game to analyse opinion formation and resistance, incorporating principles from social psychology such as confirmation bias, resource constraints, and influence penalties. Our simulation features Large Language Model (LLM) agents competing to influence a population, with penalties imposed for generating messages that propagate or counter misinformation. This framework integrates resource optimisation into the agents' decision-making process. Our findings demonstrate that while higher confirmation bias strengthens opinion alignment within groups, it also exacerbates overall polarisation. Conversely, lower confirmation bias leads to fragmented opinions and limited shifts in individual beliefs. Investing heavily in a high-resource debunking strategy can initially align the population with the debunking agent, but risks rapid resource depletion and diminished long-term influence