{"ID":2890408,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.19090","arxiv_id":"2507.19090","title":"Debating Truth: Debate-driven Claim Verification with Multiple Large Language Model Agents","abstract":"State-of-the-art single-agent claim verification methods struggle with complex claims that require nuanced analysis of multifaceted evidence. Inspired by real-world professional fact-checkers, we propose \\textbf{DebateCV}, the first debate-driven claim verification framework powered by multiple LLM agents. In DebateCV, two \\textit{Debaters} argue opposing stances to surface subtle errors in single-agent assessments. A decisive \\textit{Moderator} is then required to weigh the evidential strength of conflicting arguments to deliver an accurate verdict. Yet, zero-shot Moderators are biased toward neutral judgments, and no datasets exist for training them. To bridge this gap, we propose \\textbf{Debate-SFT}, a post-training framework that leverages synthetic data to enhance agents' ability to effectively adjudicate debates for claim verification. Results show that our methods surpass state-of-the-art non-debate approaches in both accuracy (across various evidence conditions) and justification quality.","short_abstract":"State-of-the-art single-agent claim verification methods struggle with complex claims that require nuanced analysis of multifaceted evidence. Inspired by real-world professional fact-checkers, we propose \\textbf{DebateCV}, the first debate-driven claim verification framework powered by multiple LLM agents. In DebateCV,...","url_abs":"https://arxiv.org/abs/2507.19090","url_pdf":"https://arxiv.org/pdf/2507.19090v4","authors":"[\"Haorui He\",\"Yupeng Li\",\"Dacheng Wen\",\"Yang Chen\",\"Reynold Cheng\",\"Donglong Chen\",\"Francis C. M. Lau\"]","published":"2025-07-25T09:19:25Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}