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

arXiv: https://arxiv.org/abs/2410.20140 · HTML: https://mlsanity.com/paper/2410.20140/

## Key facts

- Cited by 4 papers in the map (data through 14 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.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 22 of 22)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning](https://mlsanity.com/paper/2306.14565/) (2023)
- [Hallucination of Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2404.18930/) (2024)
- [Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?](https://mlsanity.com/paper/2011.09533/) (2020)
- [Debating with More Persuasive LLMs Leads to More Truthful Answers](https://mlsanity.com/paper/2402.06782/) (2024)
- [DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection](https://mlsanity.com/paper/2001.00179/) (2020)
- [Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory](https://mlsanity.com/paper/2310.17884/) (2023)
- [Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forward](https://mlsanity.com/paper/2103.00484/) (2021)
- [Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resources](https://mlsanity.com/paper/2112.00061/) (2021)
- [MMFakeBench: A Mixed-Source Multimodal Misinformation Detection Benchmark for LVLMs](https://mlsanity.com/paper/2406.08772/) (2024)
- [Scalable AI Safety via Doubly-Efficient Debate](https://mlsanity.com/paper/2311.14125/) (2023)
- [Detecting Photoshopped Faces by Scripting Photoshop](https://mlsanity.com/paper/1906.05856/) (2019)
- [VERITE: A Robust Benchmark for Multimodal Misinformation Detection Accounting for Unimodal Bias](https://mlsanity.com/paper/2304.14133/) (2023)
- [Synthetic Misinformers: Generating and Combating Multimodal Misinformation](https://mlsanity.com/paper/2303.01217/) (2023)
- [Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Models](https://mlsanity.com/paper/2401.13298/) (2024)
- [Interpretable Detection of Out-of-Context Misinformation with Neural-Symbolic-Enhanced Large Multimodal Model](https://mlsanity.com/paper/2304.07633/) (2023)
- [Generalization Differences between End-to-End and Neuro-Symbolic Vision-Language Reasoning Systems](https://mlsanity.com/paper/2210.15037/) (2022)
- [Exposing Text-Image Inconsistency Using Diffusion Models](https://mlsanity.com/paper/2404.18033/) (2024)

## Built on by (most cited first, 4 of 4)

- [Multi-agent Systems for Misinformation Lifecycle : Detection, Correction And Source Identification](https://mlsanity.com/paper/2505.17511/) (2025)
- [Multi-Agentic System Leveraging Open-Source LLMs to Mitigate Disinformation Threats](https://mlsanity.com/paper/2606.30259/) (2026)
- [AI Safety via Debate is Compromised by Cognitive Biases](https://mlsanity.com/paper/2610.05461/) (2026)
- [DREAM: Dynamic Resolution Assignment For Multimodal Multi-agent Debate](https://mlsanity.com/paper/2610.05615/) (2026)

## 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.