Simulating Misinformation Vulnerabilities With Agent Personas

TL;DR

This paper presents an agent-based simulation using Large Language Models to study how different personas respond to misinformation, revealing that mental schemas significantly influence interpretation more than professional background.

Contribution

It introduces a novel LLM-based agent simulation framework for misinformation response analysis, validating its alignment with human predictions and ground-truth labels.

Findings

LLM-generated agents closely match human predictions.

Mental schemas influence misinformation interpretation more than profession.

The simulation framework enables studying trust, polarization, and susceptibility.

Abstract

Disinformation campaigns can distort public perception and destabilize institutions. Understanding how different populations respond to information is crucial for designing effective interventions, yet real-world experimentation is impractical and ethically challenging. To address this, we develop an agent-based simulation using Large Language Models (LLMs) to model responses to misinformation. We construct agent personas spanning five professions and three mental schemas, and evaluate their reactions to news headlines. Our findings show that LLM-generated agents align closely with ground-truth labels and human predictions, supporting their use as proxies for studying information responses. We also find that mental schemas, more than professional background, influence how agents interpret misinformation. This work provides a validation of LLMs to be used as agents in an agent-based model of an information network for analyzing trust, polarization, and susceptibility to deceptive content in complex social systems.