Saved in:
Bibliographic Details
Main Authors: Lakara, Kumud, Channing, Georgia, Rupprecht, Christian, Sock, Juil, Torr, Philip, Collomosse, John, de Witt, Christian Schroeder
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.20140
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915532948635648
author Lakara, Kumud
Channing, Georgia
Rupprecht, Christian
Sock, Juil
Torr, Philip
Collomosse, John
de Witt, Christian Schroeder
author_facet Lakara, Kumud
Channing, Georgia
Rupprecht, Christian
Sock, Juil
Torr, Philip
Collomosse, John
de Witt, Christian Schroeder
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_20140
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MAD-Sherlock: Multi-Agent Debate for Visual Misinformation Detection
Lakara, Kumud
Channing, Georgia
Rupprecht, Christian
Sock, Juil
Torr, Philip
Collomosse, John
de Witt, Christian Schroeder
Artificial Intelligence
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.
title MAD-Sherlock: Multi-Agent Debate for Visual Misinformation Detection
topic Artificial Intelligence
url https://arxiv.org/abs/2410.20140