BiDeV: Bilateral Defusing Verification for Complex Claim Fact-Checking

2025-02-22

AI Summary

Existing fact-checking methods struggle with implicit information and multi-hop reasoning in complex claims, while also suffering from evidence redundancy, thereby limiting verification accuracy and efficiency. To address these challenges, we propose a bilateral resolution verification framework comprising two core modules: (i) an *ambiguity resolution* module that explicitly models and disambiguates the latent semantics and structural relations within claims; and (ii) a *redundancy resolution* module that orchestrates a multi-role large language model (LLM) workflow to jointly perform claim parsing, implicit information extraction, and evidence refinement. This framework is the first to emulate the stepwise verification logic of human domain experts. Evaluated on the Hover and FEVEROUS-S benchmarks under both gold-evidence and open-evidence settings, our approach achieves state-of-the-art performance, significantly improving robustness and interpretability for complex claim verification.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning
• Reasoning under Uncertainty: Other Foundations of Reasoning under Uncertainty

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Web Mining and Content Analysis: Web data provenance, reliability, and authenticity

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

Problem

• Addresses claim vagueness in fact-checking
• Reduces evidence redundancy in verification
• Enhances complex claim handling accuracy

Innovation

• LLMs for fact-checking
• Vagueness Defusing module
• Redundancy Defusing module