Towards Generalizable AI-Assisted Misinformation Inoculation: Protecting Confidence Against False Election Narratives
Abstract
We present a generalizable AI-assisted framework for rapidly generating effective "prebunking" interventions against misinformation. Like mRNA vaccine platforms, our approach uses a stable template structure that can be quickly adapted to counter emerging false narratives. In a preregistered two-wave experiment with 4,293 U.S. registered voters, we test this framework against politically-charged election misinformation -- one of the most challenging domains for misinformation intervention. Our design directly tests scalability by comparing human-reviewed and purely AI-generated inoculation messages. We find that LLM-generated prebunking significantly reduced belief in election rumors (persisting for at least one week) and increased confidence in election integrity across partisan lines. Purely AI-generated messages proved as effective as human-reviewed versions, with some achieving larger protective effects, demonstrating that effective misinformation inoculation can be achieved at machine speed without proportional human effort, offering a scalable defense against the accelerating threat of false narratives across all domains.
Keywords
Cite
@article{arxiv.2410.19202,
title = {Towards Generalizable AI-Assisted Misinformation Inoculation: Protecting Confidence Against False Election Narratives},
author = {Mitchell Linegar and Betsy Sinclair and Sander van der Linden and R. Michael Alvarez},
journal= {arXiv preprint arXiv:2410.19202},
year = {2025}
}
Comments
Version 2. Updates from previous: main independent variables are now post-treatment confidence scores, and we include pre-treatment confidence scores as a control, rather than work with difference scores. This improves power, but conclusions should otherwise be identical. Clarifications of experimental design, scalability claims, more precise phrasing of results