Check-COVID: Fact-Checking COVID-19 News Claims with Scientific Evidence
Abstract
We present a new fact-checking benchmark, Check-COVID, that requires systems to verify claims about COVID-19 from news using evidence from scientific articles. This approach to fact-checking is particularly challenging as it requires checking internet text written in everyday language against evidence from journal articles written in formal academic language. Check-COVID contains 1, 504 expert-annotated news claims about the coronavirus paired with sentence-level evidence from scientific journal articles and veracity labels. It includes both extracted (journalist-written) and composed (annotator-written) claims. Experiments using both a fact-checking specific system and GPT-3.5, which respectively achieve F1 scores of 76.99 and 69.90 on this task, reveal the difficulty of automatically fact-checking both claim types and the importance of in-domain data for good performance. Our data and models are released publicly at https://github.com/posuer/Check-COVID.
Cite
@article{arxiv.2305.18265,
title = {Check-COVID: Fact-Checking COVID-19 News Claims with Scientific Evidence},
author = {Gengyu Wang and Kate Harwood and Lawrence Chillrud and Amith Ananthram and Melanie Subbiah and Kathleen McKeown},
journal= {arXiv preprint arXiv:2305.18265},
year = {2023}
}
Comments
Accepted as ACL 2023 Findings