BiDeV: Bilateral Defusing Verification for Complex Claim Fact-Checking

TL;DR

BiDeV is a novel fact-checking framework that improves complex claim verification by addressing vagueness and redundancy through role-played LLM modules, achieving superior performance on benchmark datasets.

Contribution

Introduces BiDeV, a new fact-checking framework with modules for defusing claim vagueness and redundancy, enhancing verification accuracy for complex claims.

Findings

Achieves state-of-the-art results on Hover and Feverous-s benchmarks.

Effectively handles claim vagueness and evidence redundancy.

Demonstrates robustness under both gold and open settings.

Abstract

Complex claim fact-checking performs a crucial role in disinformation detection. However, existing fact-checking methods struggle with claim vagueness, specifically in effectively handling latent information and complex relations within claims. Moreover, evidence redundancy, where nonessential information complicates the verification process, remains a significant issue. To tackle these limitations, we propose Bilateral Defusing Verification (BiDeV), a novel fact-checking working-flow framework integrating multiple role-played LLMs to mimic the human-expert fact-checking process. BiDeV consists of two main modules: Vagueness Defusing identifies latent information and resolves complex relations to simplify the claim, and Redundancy Defusing eliminates redundant content to enhance the evidence quality. Extensive experimental results on two widely used challenging fact-checking benchmarks (Hover and Feverous-s) demonstrate that our BiDeV can achieve the best performance under both gold and open settings. This highlights the effectiveness of BiDeV in handling complex claims and ensuring precise fact-checking