Perception, Understanding and Reasoning, A Multimodal Benchmark for Video Fake News Detection
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_ | 1866918294480486400 |
|---|---|
| author | Yakun, Cui Qi, Peng Huo, Fushuo Du, Hang Shi, Weijie Dai, Juntao Zhu, Zhenghao Han, Sirui Guo, Yike |
| author_facet | Yakun, Cui Qi, Peng Huo, Fushuo Du, Hang Shi, Weijie Dai, Juntao Zhu, Zhenghao Han, Sirui Guo, Yike |
| contents | The advent of multi-modal large language models (MLLMs) has greatly advanced research on video fake news detection (VFND) tasks. Existing benchmarks typically focus on the detection accuracy, while failing to provide fine-grained assessments for the entire detection process. To address these limitations, we introduce {POVFNDB (Process-oriented Video Fake News Detection Benchmark)}, a process-oriented benchmark comprising 10 tasks designed to systematically evaluate MLLMs' perception, understanding, and reasoning capabilities in VFND. This benchmark contains \textit{36,240} human-annotated question-answer (QA) in structured or open-ended formats, spanning 15 distinct evaluation dimensions that characterize different aspects of the video fake news detection process. Using POVFNDB, we conduct comprehensive evaluations on both proprietary and open-source MLLMs. Moreover, we establish a strong benchmark baseline by fine-tuning Qwen2.5VL-7B-Instruct on process-oriented chain-of-thought data constructed with our proposed POVFND-CoT framework, achieving state-of-the-art performance on VFND. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_24816 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Perception, Understanding and Reasoning, A Multimodal Benchmark for Video Fake News Detection Yakun, Cui Qi, Peng Huo, Fushuo Du, Hang Shi, Weijie Dai, Juntao Zhu, Zhenghao Han, Sirui Guo, Yike Computer Vision and Pattern Recognition Artificial Intelligence The advent of multi-modal large language models (MLLMs) has greatly advanced research on video fake news detection (VFND) tasks. Existing benchmarks typically focus on the detection accuracy, while failing to provide fine-grained assessments for the entire detection process. To address these limitations, we introduce {POVFNDB (Process-oriented Video Fake News Detection Benchmark)}, a process-oriented benchmark comprising 10 tasks designed to systematically evaluate MLLMs' perception, understanding, and reasoning capabilities in VFND. This benchmark contains \textit{36,240} human-annotated question-answer (QA) in structured or open-ended formats, spanning 15 distinct evaluation dimensions that characterize different aspects of the video fake news detection process. Using POVFNDB, we conduct comprehensive evaluations on both proprietary and open-source MLLMs. Moreover, we establish a strong benchmark baseline by fine-tuning Qwen2.5VL-7B-Instruct on process-oriented chain-of-thought data constructed with our proposed POVFND-CoT framework, achieving state-of-the-art performance on VFND. |
| title | Perception, Understanding and Reasoning, A Multimodal Benchmark for Video Fake News Detection |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2510.24816 |