Belief-Sim: Towards Belief-Driven Simulation of Demographic Misinformation Susceptibility

Researchers introduce BeliefSim, a framework that uses Large Language Models to simulate how different demographic groups are susceptible to misinformation based on their underlying beliefs. The system achieves up to 92% accuracy in predicting misinformation susceptibility by incorporating psychology-informed belief profiles.

• →BeliefSim framework can simulate demographic misinformation susceptibility with up to 92% accuracy using LLMs.
• →The system uses psychology-informed taxonomies and survey data to construct demographic belief profiles.
• →Beliefs serve as a strong predictive factor for determining misinformation susceptibility across different groups.
• →The research employs both prompt-based conditioning and post-training adaptation methods.
• →The framework addresses the growing societal threat of misinformation by understanding demographic variations in susceptibility.