FactGenius: Combining Zero-Shot Prompting and Fuzzy Relation Mining to Improve Fact Verification with Knowledge Graphs
Abstract: Fact-checking is a crucial natural language processing (NLP) task that verifies the truthfulness of claims by considering reliable evidence. Traditional methods are labour-intensive, and most automatic approaches focus on using documents as evidence. In this paper, we focus on the relatively under-researched fact-checking with Knowledge Graph data as evidence and experiment on the recently introduced FactKG benchmark. We present FactGenius, a novel method that enhances fact-checking by combining zero-shot prompting of large language models (LLMs) with fuzzy text matching on knowledge graphs (KGs). Our method employs LLMs for filtering relevant connections from the graph and validates these connections via distance-based matching. The evaluation of FactGenius on an existing benchmark demonstrates its effectiveness, as we show it significantly outperforms state-of-the-art methods.
Paper Type: Long
Research Area: NLP Applications
Research Area Keywords: fact checking, knowledge graphs
Contribution Types: NLP engineering experiment
Languages Studied: English
Submission Number: 2087
Loading