A New Dataset and Benchmark for Grounding Multimodal Misinformation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916943390310400 |
|---|---|
| author | Yang, Bingjian Xu, Danni Niu, Kaipeng Liu, Wenxuan Wang, Zheng Kankanhalli, Mohan |
| author_facet | Yang, Bingjian Xu, Danni Niu, Kaipeng Liu, Wenxuan Wang, Zheng Kankanhalli, Mohan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_08008 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A New Dataset and Benchmark for Grounding Multimodal Misinformation Yang, Bingjian Xu, Danni Niu, Kaipeng Liu, Wenxuan Wang, Zheng Kankanhalli, Mohan Social and Information Networks Artificial Intelligence Multimedia 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. |
| title | A New Dataset and Benchmark for Grounding Multimodal Misinformation |
| topic | Social and Information Networks Artificial Intelligence Multimedia |
| url | https://arxiv.org/abs/2509.08008 |