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

ArXi:2603.03585v2 Announce Type: replace-cross Misinformation is a growing societal threat, and susceptibility to misinformative claims varies across graphic groups due to differences in underlying beliefs. As Large Language Models (LLMs) are increasingly used to simulate human behaviors, we investigate whether they can simulate graphic misinformation susceptibility, treating beliefs as a primary driving factor. We