From Manipulation to Mistrust: Explaining Diverse Micro-Video Misinformation for Robust Debunking in the Wild

TL;DR

This paper introduces WildFakeBench, a comprehensive benchmark for diverse micro-video misinformation, and FakeAgent, a multi-agent framework that improves detection and attribution of various misinformation types in real-world scenarios.

Contribution

The paper presents WildFakeBench, a large-scale, annotated micro-video misinformation benchmark, and FakeAgent, a novel multi-agent reasoning framework for fine-grained attribution and detection.

Findings

FakeAgent outperforms existing models across misinformation types.

WildFakeBench offers a realistic, challenging testbed for detection.

FakeAgent effectively integrates multimodal content and external evidence.

Abstract

The rise of micro-videos has reshaped how misinformation spreads, amplifying its speed, reach, and impact on public trust. Existing benchmarks typically focus on a single deception type, overlooking the diversity of real-world cases that involve multimodal manipulation, AI-generated content, cognitive bias, and out-of-context reuse. Meanwhile, most detection models lack fine-grained attribution, limiting interpretability and practical utility. To address these gaps, we introduce WildFakeBench, a large-scale benchmark of over 10,000 real-world micro-videos covering diverse misinformation types and sources, each annotated with expert-defined attribution labels. Building on this foundation, we develop FakeAgent, a Delphi-inspired multi-agent reasoning framework that integrates multimodal understanding with external evidence for attribution-grounded analysis. FakeAgent jointly analyzes content and retrieved evidence to identify manipulation, recognize cognitive and AI-generated patterns, and detect out-of-context misinformation. Extensive experiments show that FakeAgent consistently outperforms existing MLLMs across all misinformation types, while WildFakeBench provides a realistic and challenging testbed for advancing explainable micro-video misinformation detection. Data and code are available at: https://github.com/Aiyistan/FakeAgent.