FACT-GPT: Fact-Checking Augmentation Via Claim Matching with LLMs

Our society is facing rampant misinformation harming public health and trust.To address the societal challenge, we introduce FACT-GPT, a system leveragingLarge Language Models (LLMs) to automate the claim matching stage offact-checking. FACT-GPT, trained on a synthetic dataset, identifies socialmedia content that aligns with, contradicts, or is irrelevant to previouslydebunked claims. Our evaluation shows that our specialized LLMs can match theaccuracy of larger models in identifying related claims, closely mirroringhuman judgment. This research provides an automated solution for efficientclaim matching, demonstrates the potential of LLMs in supporting fact-checkers,and offers valuable resources for further research in the field.