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.
@article{arxiv.2510.24816,
title = {Perception, Understanding and Reasoning, A Multimodal Benchmark for Video Fake News Detection},
author = {Cui Yakun and Peng Qi and Fushuo Huo and Hang Du and Weijie Shi and Juntao Dai and Zhenghao Zhu and Sirui Han and Yike Guo},
journal= {arXiv preprint arXiv:2510.24816},
year = {2026}
}