Belief-Sim: Towards Belief-Driven Simulation of Demographic Misinformation Susceptibility
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917532741402624 |
|---|---|
| author | Borah, Angana Khan, Zohaib Mihalcea, Rada Pérez-Rosas, Verónica |
| author_facet | Borah, Angana Khan, Zohaib Mihalcea, Rada Pérez-Rosas, Verónica |
| contents | 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 misinformation taxonomies and survey priors. We study prompt-based conditioning and post-training adaptation, and conduct a multi-fold evaluation using: (i) susceptibility alignment and (ii) counterfactual demographic sensitivity. Across both datasets and modeling strategies, we show that beliefs provide a strong prior for simulating misinformation susceptibility, with alignment up to 92%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_03585 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Belief-Sim: Towards Belief-Driven Simulation of Demographic Misinformation Susceptibility Borah, Angana Khan, Zohaib Mihalcea, Rada Pérez-Rosas, Verónica Computation and Language Artificial Intelligence 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 misinformation taxonomies and survey priors. We study prompt-based conditioning and post-training adaptation, and conduct a multi-fold evaluation using: (i) susceptibility alignment and (ii) counterfactual demographic sensitivity. Across both datasets and modeling strategies, we show that beliefs provide a strong prior for simulating misinformation susceptibility, with alignment up to 92%. |
| title | Belief-Sim: Towards Belief-Driven Simulation of Demographic Misinformation Susceptibility |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2603.03585 |