MAD-Sherlock：面向视觉错误信息检测的多智能体辩论系统
MAD-Sherlock: Multi-Agent Debate for Visual Misinformation Detection
AI总结：
针对现有视觉错误信息检测系统泛化性差、可解释性不足的问题，提出无需微调的多智能体辩论系统MAD-Sherlock，通过多模态智能体辩论与外部信息检索实现跨语境推理，在三个基准上性能均优于现有方法，且能提升用户信任。
摘要：
最具挑战性的错误信息形式之一是将图像与误导性文本配对以构建虚假叙事。现有的人工智能驱动检测系统通常需要针对特定领域进行微调，这限制了其泛化能力，且几乎无法为决策提供解释，阻碍了用户信任与实际应用。我们提出MAD-Sherlock，一种用于检测脱离语境类错误信息的多智能体辩论系统。该系统将检测任务构建为多智能体辩论过程，还原了网络上多样且冲突的话语环境。多模态智能体协同评估语境一致性，并检索外部信息以支持跨语境推理。该框架不依赖特定领域与时间，无需微调即可达到最先进的检测准确率，并能提供深度解释。在NewsCLIPpings、VERITE和MMFakeBench三个基准数据集上的评估显示，其性能分别优于现有方法2%、3%和5%。消融实验与用户研究表明，辩论机制及生成的解释显著提升了检测性能，同时增强了专家与非专家用户的信任度，使MAD-Sherlock成为自主公民智能领域的可靠工具。
英文摘要：
One of the most challenging forms of misinformation involves pairing images with misleading text to create false narratives. Existing AI-driven detection systems often require domain-specific finetuning, limiting generalizability, and offer little insight into their decisions, hindering trust and adoption. We introduce MAD-Sherlock, a multi-agent debate system for out-of-context misinformation detection. MAD-Sherlock frames detection as a multi-agent debate, reflecting the diverse and conflicting discourse found online. Multimodal agents collaborate to assess contextual consistency and retrieve external information to support cross-context reasoning. Our framework is domain- and time-agnostic, requiring no finetuning, yet achieves state-of-the-art accuracy with in-depth explanations. Evaluated on NewsCLIPpings, VERITE, and MMFakeBench, it outperforms prior methods by 2%, 3%, and 5%, respectively. Ablation and user studies show that the debate and resultant explanations significantly improve detection performance and improve trust for both experts and non-experts, positioning MAD-Sherlock as a robust tool for autonomous citizen intelligence.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
