paper-with-me

Papers

A New Dataset and Benchmark for Grounding Multimodal Misinformation

2025-09-08 · Bingjian Yang, Danni Xu, Kaipeng Niu, Wenxuan Liu, Zheng Wang, Mohan Kankanhalli arxiv

The proliferation of online misinformation videos poses serious societal risks. Current datasets and detection methods primarily target binary classification or single-modality localization based on post-processed data, lacking the interpretability needed to counter persuasive misinformation. In this paper, we introduce the task of Grounding Multimodal Misinformation (GroundMM), which verifies multimodal content and localizes misleading segments across modalities. We present the first real-world dataset for this task, GroundLie360, featuring a taxonomy of misinformation types, fine-grained annotations across text, speech, and visuals, and validation with Snopes evidence and annotator reasoning. We also propose a VLM-based, QA-driven baseline, FakeMark, using single- and cross-modal cues for effective detection and grounding. Our experiments highlight the challenges of this task and lay a foundation for explainable multimodal misinformation detection.

📄 PDF Abstract BibTeX arXiv:2509.08008

Code (0)

등록된 구현이 없습니다.

Tasks

Binary Classification

Similar Papers 제목 키워드 기반

RAMA: Retrieval-Augmented Multi-Agent Framework for Misinformation Detection in Multimodal Fact-Checking

2025-07-12 · Shuo Yang, Zijian Yu, Zhenzhe Ying, Yuqin Dai 외 arxiv

The rapid proliferation of multimodal misinformation presents significant challenges for automated fact-checking systems, especially when claims are ambiguous or lack sufficient context. We introduce RAMA, a novel retrie…

LADLE-MM: Limited Annotation based Detector with Learned Ensembles for Multimodal Misinformation

2025-12-23 · Daniele Cardullo, Simone Teglia, Irene Amerini arxiv

With the rise of easily accessible tools for generating and manipulating multimedia content, realistic synthetic alterations to digital media have become a widespread threat, often involving manipulations across multiple…

Multi-Label Classification

RW-Post: Auditable Evidence-Grounded Multimodal Fact-Checking in the Wild

2026-05-11 · Danni Xu, Shaojing Fan, Harry Cheng, Mohan Kankanhalli arxiv

Multimodal misinformation increasingly leverages visual persuasion, where repurposed or manipulated images strengthen misleading text. We introduce \textbf{RW-Post}, a post-aligned \textbf{text--image benchmark} for real…

Visual Grounding

RW-Post: Auditable Evidence-Grounded Multimodal Fact-Checking in the Wild

2025-12-28 · Danni Xu, Shaojing Fan, Harry Cheng, Mohan Kankanhalli arxiv

Multimodal misinformation increasingly leverages visual persuasion, where repurposed or manipulated images strengthen misleading text. We introduce RW-Post, a post-aligned text--image benchmark for real-world multimodal …

Visual Grounding

From Generation to Detection: A Multimodal Multi-Task Dataset for Benchmarking Health Misinformation

2025-05-24 · Zhihao Zhang, Yiran Zhang, Xiyue Zhou, Liting Huang 외

Infodemics and health misinformation have significant negative impact on individuals and society, exacerbating confusion and increasing hesitancy in adopting recommended health measures. Recent advancements in generative…

ArticlesBenchmarkingFact CheckingMisinformation