CRAVE: A Conflicting Reasoning Approach for Explainable Claim Verification Using LLMs

The rapid spread of misinformation, amplified by digital media and AI-generated content, has made automated claim verification increasingly crucial. Traditional methods relying on expert-annotated evidence are labor-intensive and lack scalability, while recent automated systems still struggle with complex claims requiring nuanced reasoning. To address this, we propose CRAVE (Conflicting Reasoning Approach for explainable claim VErification), a novel framework that leverages conflicting rationales generated by large language models (LLMs) for explainable and accurate claim verification. CRAVE comprises three modules: (1) Ambiguity-Elimination Enhanced Evidence Retrieval, which refines entity-based searches to collect relevant evidence from sources like Wikipedia; (2) Conflicting Perspective Reasoning and Preliminary Judgment, where LLMs reason across four dimensions—direct evidence, semantic relationships, linguistic cues, and logical inference—to produce preliminary judgments; (3) Small Language Model (SLM)-based Judge, which is fine-tuned to assess the confidence of conflicting rationales and deliver a final authenticity verdict. Experiments on two public claim verification datasets show that CRAVE significantly outperforms state-of-the-art baselines, with enhanced evidence retrieval and more interpretable predictions. Code is available at: https://github.com/8zym/CRAVE.