BiDeV: Bilateral Defusing Verification for Complex Claim Fact-Checking

TL;DR

BiDeV addresses the challenge of complex claim fact-checking where vagueness and redundant evidence hinder verification. It introduces Vagueness Defusing to perceive latent information and resolve relations, and Redundancy Defusing to filter evidence, powered by coordinated role-play among multiple LLMs. On the Hover and Feverous-s benchmarks, BiDeV achieves the best Macro-F1 under both gold and open settings, with a notable 3.88 percentage point gain. The framework demonstrates how structured defusing workflows can emulate human expert verification and improve reliability for disinformation detection.

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

Figures (7)

• Figure 1: An example illustrating how the claim vagueness impedes the fact-checking process. Latent information encompasses unresolved entities and undetermined attributes; Complex relations include referential relations and comparative relations.
• Figure 2: The overview of our BiDeV. Two main modules for Bilateral Defusing Verification: (a) Vagueness Defusing for input claim. Perceive-then-rewrite stage simplifies the claim iteratively: the perceptor perceives questions about latent information, the querier provides explicit knowledge to the question and the rewriter rewrites the latent information in the claim with the explicit knowledge. Decompose-then-check stage verifies the claim: the decomposer splits several sub-claims and the checker verifies the sub-claims. (b) Redundancy Defusing for evidence. The evidence extracted from the source is refined by the filter.
• Figure 3: Ablation study on Hover and Feverous-S. $M_f$: Filter; $M_p$: Perceptor; $M_r$: Rewriter; $M_d$: Decomposer.
• Figure 4: Analysis of Redundancy Defusing under different Top-K retrieved evidence.
• Figure 5: Analysis of different model scales in Querier and Checker: FLAN-T5-small (80M), FLAN-T5-base (250M), FLAN-T5-large (780M), FLAN-T5-XL (3B), FLAN-T5-XXL (11B) on Hover 2-hop, 3-hop, and 4-hop subsets.