MAD-Sherlock: Multi-Agent Debates for Out-of-Context Misinformation Detection
Lakara, Kumud, Sock, Juil, Rupprecht, Christian, Torr, Philip, Collomosse, John, de Witt, Christian Schroeder
–arXiv.org Artificial Intelligence
One of the most challenging forms of misinformation involves the out-of-context (OOC) use of images paired with misleading text, creating false narratives. Existing AI-driven detection systems lack explainability and require expensive fine-tuning. We address these issues with MAD-Sherlock: a Multi-Agent Debate system for OOC Misinformation Detection. MAD-Sherlock introduces a novel multi-agent debate framework where multimodal agents collaborate to assess contextual consistency and request external information to enhance cross-context reasoning and decision-making. Our framework enables explainable detection with state-of-the-art accuracy even without domain-specific fine-tuning. Extensive ablation studies confirm that external retrieval significantly improves detection accuracy, and user studies demonstrate that MAD-Sherlock boosts performance for both experts and non-experts. These results position MAD-Sherlock as a powerful tool for autonomous and citizen intelligence applications.
arXiv.org Artificial Intelligence
Oct-26-2024
- Country:
- Asia > Russia (0.14)
- North America > United States
- New York > New York County
- New York City (0.04)
- Massachusetts > Middlesex County
- Cambridge (0.04)
- California > Santa Clara County
- San Jose (0.04)
- New York > New York County
- Europe
- Ukraine (0.04)
- United Kingdom > England
- Oxfordshire > Oxford (0.04)
- Bulgaria > Sofia City Province
- Sofia (0.04)
- Genre:
- Research Report > Experimental Study (0.67)
- Technology: