@inproceedings{yakun-etal-2026-perception,
title = "Perception, Understanding and Reasoning: A Multimodal Benchmark for Video Fake News Detection",
author = "Yakun, Cui and
Qi, Peng and
Huo, Fushuo and
Du, Hang and
Shi, Weijie and
Dai, Juntao and
Zhu, Zhenghao and
Han, Sirui",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.2103/",
pages = "45332--45363",
ISBN = "979-8-89176-390-6",
abstract = "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 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 fine-tune Qwen2.5VL-7B-Instruct on a reasoning dataset generated by our proposed POVFND-CoT, a chain-of-thought method that utilizes rationales from evaluation results and rationale validation. The resulting model achieves sota performance on VFND."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yakun-etal-2026-perception">
<titleInfo>
<title>Perception, Understanding and Reasoning: A Multimodal Benchmark for Video Fake News Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cui</namePart>
<namePart type="family">Yakun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peng</namePart>
<namePart type="family">Qi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fushuo</namePart>
<namePart type="family">Huo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hang</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weijie</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juntao</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenghao</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sirui</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>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 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 fine-tune Qwen2.5VL-7B-Instruct on a reasoning dataset generated by our proposed POVFND-CoT, a chain-of-thought method that utilizes rationales from evaluation results and rationale validation. The resulting model achieves sota performance on VFND.</abstract>
<identifier type="citekey">yakun-etal-2026-perception</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.2103/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>45332</start>
<end>45363</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Perception, Understanding and Reasoning: A Multimodal Benchmark for Video Fake News Detection
%A Yakun, Cui
%A Qi, Peng
%A Huo, Fushuo
%A Du, Hang
%A Shi, Weijie
%A Dai, Juntao
%A Zhu, Zhenghao
%A Han, Sirui
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F yakun-etal-2026-perception
%X 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 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 fine-tune Qwen2.5VL-7B-Instruct on a reasoning dataset generated by our proposed POVFND-CoT, a chain-of-thought method that utilizes rationales from evaluation results and rationale validation. The resulting model achieves sota performance on VFND.
%U https://aclanthology.org/2026.acl-long.2103/
%P 45332-45363
Markdown (Informal)
[Perception, Understanding and Reasoning: A Multimodal Benchmark for Video Fake News Detection](https://aclanthology.org/2026.acl-long.2103/) (Yakun et al., ACL 2026)
ACL
- Cui Yakun, Peng Qi, Fushuo Huo, Hang Du, Weijie Shi, Juntao Dai, Zhenghao Zhu, and Sirui Han. 2026. Perception, Understanding and Reasoning: A Multimodal Benchmark for Video Fake News Detection. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 45332–45363, San Diego, California, United States. Association for Computational Linguistics.