mlsanityData to 7 Oct 2026

MAD-Sherlock: Multi-Agent Debate for Visual Misinformation Detection

arXiv 2410.20140 ↗First posted 26 Oct 2024cs.AIcited by 2

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 22 of its 43 references that are in the map. First posted on arXiv 26 Oct 2024.

Builds on

22 of 43 references.

References · 22

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  5. 2019VisualBERT: A Simple and Performant Baseline for Vision and Languagecited by 1,291
  6. 2023Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuningcited by 439
  7. 2024Hallucination of Multimodal Large Language Models: A Surveycited by 380
  8. 2020Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?cited by 281
  9. 2024Debating with More Persuasive LLMs Leads to More Truthful Answerscited by 255
  10. 2020DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detectioncited by 231
  11. 2023Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theorycited by 218
  12. 2021Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forwardcited by 82
10 more
  1. 2021Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resourcescited by 71
  2. 2024MMFakeBench: A Mixed-Source Multimodal Misinformation Detection Benchmark for LVLMscited by 60
  3. 2019Detecting Photoshopped Faces by Scripting Photoshopcited by 55
  4. 2023Scalable AI Safety via Doubly-Efficient Debatecited by 54
  5. 2023VERITE: A Robust Benchmark for Multimodal Misinformation Detection Accounting for Unimodal Biascited by 37
  6. 2023Synthetic Misinformers: Generating and Combating Multimodal Misinformationcited by 23
  7. 2024Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Modelscited by 17
  8. 2023Interpretable Detection of Out-of-Context Misinformation with Neural-Symbolic-Enhanced Large Multimodal Modelcited by 8
  9. 2022Generalization Differences between End-to-End and Neuro-Symbolic Vision-Language Reasoning Systemscited by 6
  10. 2024Exposing Text-Image Inconsistency Using Diffusion Modelscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Multi-agent Systems for Misinformation Lifecycle : Detection, Correction And Source Identificationcited by 2
  2. 2026Multi-Agentic System Leveraging Open-Source LLMs to Mitigate Disinformation Threatscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Agentic Mixed-Source Multi-Modal Misinformation Detection with Adaptive Test-Time Scaling
  2. 2025EXCLAIM: An Explainable Cross-Modal Agentic System for Misinformation Detection with Hierarchical Retrieval
  3. 2025Debate-to-Detect: Reformulating Misinformation Detection as a Real-World Debate with Large Language Models
  4. 2025Beyond Detection: Exploring Evidence-based Multi-Agent Debate for Misinformation Intervention and Persuasion
  5. 2025MV-Debate: Multi-view Agent Debate with Dynamic Reflection Gating for Multimodal Harmful Content Detection in Social Media
  6. 2025RAMA: Retrieval-Augmented Multi-Agent Framework for Misinformation Detection in Multimodal Fact-Checking
  7. 2026FactGuard: Agentic Video Misinformation Detection via Reinforcement Learning
  8. 2025The Truth Becomes Clearer Through Debate! Multi-Agent Systems with Large Language Models Unmask Fake News