Abstract

Our society is facing rampant misinformation harming public health and trust. To address the societal challenge, we introduce FACT-GPT, a framework leveraging Large Language Models (LLMs) to assist fact-checking. FACT-GPT, trained on a synthetic dataset, identifies social media content that aligns with, contradicts, or is irrelevant to previously debunked claims. Our evaluation shows that our specialized LLMs can match the accuracy of larger models in identifying related claims, closely mirroring human judgment. This research provides a solution for efficient claim matching, demonstrates the potential of LLMs in supporting fact-checkers, and offers valuable resources for further research in the field.

Date

February 8, 2024

Authors

Eun Cheol Choi, Emilio Ferrara

Conference

WWW '24: Companion Proceedings of the ACM Web Conference 2024