A Graph-based Verification Framework for Fact-Checking
This work improves fact-checking accuracy for combating misinformation, representing an incremental advancement over existing LLM-based methods.
The paper tackles limitations in fact-checking methods using LLMs by proposing GraphFC, a graph-based framework that addresses insufficient claim decomposition and mention ambiguity through claim and evidence graphs with triplets, achieving state-of-the-art performance on three datasets.
Fact-checking plays a crucial role in combating misinformation. Existing methods using large language models (LLMs) for claim decomposition face two key limitations: (1) insufficient decomposition, introducing unnecessary complexity to the verification process, and (2) ambiguity of mentions, leading to incorrect verification results. To address these challenges, we suggest introducing a claim graph consisting of triplets to address the insufficient decomposition problem and reduce mention ambiguity through graph structure. Based on this core idea, we propose a graph-based framework, GraphFC, for fact-checking. The framework features three key components: graph construction, which builds both claim and evidence graphs; graph-guided planning, which prioritizes the triplet verification order; and graph-guided checking, which verifies the triples one by one between claim and evidence graphs. Extensive experiments show that GraphFC enables fine-grained decomposition while resolving referential ambiguities through relational constraints, achieving state-of-the-art performance across three datasets.