Enhancing fact-checking with RAG and knowledge graphs

Abstract

Traditional fact-checking methods, while effective, are often too slow to keep up with the speed at which false information circulates online. In recent years, artificial intelligence (AI) has gained popularity as a means of automating the fact-checking process, particularly large language models (LLMs). Although LLMs have demonstrated efficacy in assisting with verification tasks, they are constrained by factors such as the quality of training data and their ability to retrieve pertinent information for verification. They are also prone to ‘hallucinations’, generating plausible but false or misleading information, raising critical concerns about their reliability as independent fact-checkers. This paper explores a hybrid approach that combines retrieval-augmented generation (RAG) with knowledge graphs (KGs) and OpenCTI, a platform for cyber threat intelligence. This approach ensures that the final output is not only informative but also transparent, linking claims to authoritative sources. This makes it a valuable tool for journalists, fact-checkers, or the general public, who increasingly require timely and reliable answers in an information environment shaped by disinformation.