Simulating Misinformation Vulnerabilities With Agent Personas
This work addresses the challenge of studying misinformation vulnerabilities for researchers and policymakers, offering a validated simulation tool as an alternative to real-world experimentation, though it is incremental in applying existing LLM methods to this domain.
The paper tackled the problem of understanding how different populations respond to misinformation by developing an agent-based simulation using Large Language Models (LLMs) to model reactions to news headlines, finding that LLM-generated agents align closely with ground-truth labels and human predictions and that mental schemas influence interpretations more than professional background.
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.