用多智能体辩论检测图文误导信息，无需微调且解释清晰。
MAD-Sherlock: Multi-Agent Debate for Visual Misinformation Detection
- 多个视觉语言智能体辩论图文一致性，跨上下文检索证据
- 在三个数据集上准确率领先2%-5%，无需领域微调
- 适合需要可解释性与泛化能力的新闻审核与公众识谣场景
图文误导信息是虚假叙事的主要形式。现有AI检测系统通常需特定领域微调，通用性差，且决策过程不透明。我们提出MAD-Sherlock，一种面向非上下文误导信息检测的多智能体辩论系统。该系统将检测任务建模为多智能体间的辩论，模拟网络上的多元冲突讨论。多个多模态智能体协作评估图文一致性，并检索外部信息以支持跨上下文推理。该框架具备领域和时间无关性，无需微调即可达到顶尖准确率，并提供深度解释。在NewsCLIPpings、VERITE和MMFakeBench三个数据集上，其性能分别优于先前方法2%、3%和5%。消融实验与用户研究显示，辩论机制与解释显著提升检测效果及专家与普通用户信任度，使MAD-Sherlock成为自主公民智能的有力工具。
原文摘要 · Abstract (English)
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.
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。