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

ACL ARR 2026 January Submission7469 Authors

Keywords: belief-based learning, demographic misinformation susceptibility, counterfactual evaluation, belief-based fine-tuning

Abstract: Misinformation is a growing societal threat, and susceptibility to misinformative claims varies across demographic 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 demographic misinformation susceptibility, treating beliefs as a primary driving factor. We introduce BeliefSim, a simulation framework that constructs demographic belief profiles using psychology-informed taxonomies and survey priors. We study prompt-based conditioning and post-training adaptation, and conduct a multi-fold evaluation using: (i) susceptibility accuracy and (ii) counterfactual demographic sensitivity. Across both datasets and modeling strategies, we show that beliefs provide a strong prior for simulating misinformation susceptibility, with accuracy up to 92\%.

Paper Type: Long

Research Area: AI/LLM Agents

Research Area Keywords: LLM agents, LLM simulation, Agent evaluation, Safety and alignment for agents

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Data analysis

Languages Studied: English

Submission Number: 7469