You Can't Fool Us: Understanding the Resilience of LLM-driven Agent Communities to Misinformation

TL;DR

This study uses an LLM-based agent simulation to analyze how community traits like open-mindedness and political ideology influence resilience to misinformation, highlighting mechanisms and intervention effects.

Contribution

It introduces a synthetic community simulation framework to examine the joint impact of evidence-seeking traits and political ideology on misinformation response and correction.

Findings

Higher Actively Open-minded Thinking (AOT) enhances resistance and recovery from misinformation.

Moderate communities recover more reliably than polarized ones.

Interventions like persuasion and fact-checking improve post-peak correction effectiveness.

Abstract

Misinformation resilience is a dynamic community process: communities differ not only in whether they initially trust false claims, but also in how they recover through interaction, questioning, correction, and support withdrawal. We study this process with an LLM-based agent simulation that constructs synthetic communities along two theoretically motivated dimensions: Actively Open-minded Thinking (AOT), which captures evidence-seeking and willingness to revise beliefs, and Political Ideology (PI), which captures identity-based interpretation of contested claims. These two traits allow us to examine how evidence-oriented reasoning and ideological alignment jointly shape community responses to credible misinformation shocks. Across systematically varied AOT-PI communities, we find that higher AOT improves both resistance to misinformation uptake and recovery after trust peaks. PI shapes the recovery pathway: ideologically moderate communities recover more reliably, while polarized communities retain more residual support. Stance-level analysis shows that resilience depends on whether agents move from questioning a claim to denying or correcting it and withdrawing prior support. Intervention experiments further show that persuasion and fact checking better support post-peak correction, whereas accuracy prompts mainly induce early caution and source warnings have weaker effects. Together, this work provides a mechanism-level account of community misinformation resilience, showing how psychological composition and intervention design shape whether communities move from misinformation exposure toward correction or persistent support.