用多智能体辩论检测健康谣言，先评分后辩论，提升判断准确性。
Exploring Health Misinformation Detection with Multi-Agent Debate
- 先用大模型评估文章立场，计算共识得分
- 得分低时触发多智能体辩论，生成有依据的结论
- 适合需要高可信度验证的健康信息场景
随着网络上健康谣言泛滥，事实核查愈发重要。有效验证需高质量证据与严谨推理。本文提出两阶段健康谣言检测框架：先预测共识得分，再启动多智能体辩论。第一阶段使用大语言模型（LLMs）独立评估检索到的文章，计算聚合共识得分；若得分低于阈值，则进入第二阶段。多个智能体进行结构化辩论，整合矛盾证据，生成具有明确理由的合理判决。实验表明，该两阶段方法优于基线模型，凸显了自动化评分与协作推理结合在复杂验证任务中的价值。
原文摘要 · Abstract (English)
Fact-checking health-related claims has become increasingly critical as misinformation proliferates online. Effective verification requires both the retrieval of high-quality evidence and rigorous reasoning processes. In this paper, we propose a two-stage framework for health misinformation detection: Agreement Score Prediction followed by Multi-Agent Debate. In the first stage, we employ large language models (LLMs) to independently evaluate retrieved articles and compute an aggregated agreement score that reflects the overall evidence stance. When this score indicates insufficient consensus-falling below a predefined threshold-the system proceeds to a second stage. Multiple agents engage in structured debate to synthesize conflicting evidence and generate well-reasoned verdicts with explicit justifications. Experimental results demonstrate that our two-stage approach achieves superior performance compared to baseline methods, highlighting the value of combining automated scoring with collaborative reasoning for complex verification tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。