@inproceedings{zeng-etal-2026-detection,
title = "From Detection to Understanding: Multi-Turn Reasoning for Video Misinformation Analysis",
author = "Zeng, Zhi and
Wu, Jiaying and
Luo, Minnan and
Zhang, Di and
Yang, Yifei and
Kong, Xiangzheng and
Wan, Herun and
Ma, Zihan",
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.1716/",
pages = "37009--37027",
ISBN = "979-8-89176-390-6",
abstract = "Video misinformation detection is often approached as a binary veracity classification problem, overlooking the complex reasoning required to explain how and why content misleads. Existing benchmarks fail to capture the diversity of manipulation strategies, such as AI-generated edits and out-of-context manipulation, and do not evaluate whether models can provide process-level justifications for their judgments. We address these limitations with MisVideoQA, a multi-turn benchmark designed to assess comprehensive understanding and reasoning in video misinformation analysis. MisVideoQA covers 12 fine-grained deception categories and evaluates models along six dimensions, progressing from perceptual attribution to intent and persuasion analysis. Recognizing that standard MLLMs struggle to sustain such structured, evidence-based deduction, we propose MisAgent, a Delphi-inspired multi-agent framework in which specialized agents collaboratively integrate multimodal cues with external evidence. Experimental results show that state-of-the-art multimodal large language models perform poorly on MisVideoQA, while MisAgent consistently improves reasoning accuracy and explanation quality. Together, our benchmark and framework establish a unified foundation for reliable, interpretable, and evidence-grounded video misinformation analysis."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zeng-etal-2026-detection">
<titleInfo>
<title>From Detection to Understanding: Multi-Turn Reasoning for Video Misinformation Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhi</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaying</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minnan</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Di</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yifei</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiangzheng</namePart>
<namePart type="family">Kong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Herun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zihan</namePart>
<namePart type="family">Ma</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>Video misinformation detection is often approached as a binary veracity classification problem, overlooking the complex reasoning required to explain how and why content misleads. Existing benchmarks fail to capture the diversity of manipulation strategies, such as AI-generated edits and out-of-context manipulation, and do not evaluate whether models can provide process-level justifications for their judgments. We address these limitations with MisVideoQA, a multi-turn benchmark designed to assess comprehensive understanding and reasoning in video misinformation analysis. MisVideoQA covers 12 fine-grained deception categories and evaluates models along six dimensions, progressing from perceptual attribution to intent and persuasion analysis. Recognizing that standard MLLMs struggle to sustain such structured, evidence-based deduction, we propose MisAgent, a Delphi-inspired multi-agent framework in which specialized agents collaboratively integrate multimodal cues with external evidence. Experimental results show that state-of-the-art multimodal large language models perform poorly on MisVideoQA, while MisAgent consistently improves reasoning accuracy and explanation quality. Together, our benchmark and framework establish a unified foundation for reliable, interpretable, and evidence-grounded video misinformation analysis.</abstract>
<identifier type="citekey">zeng-etal-2026-detection</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.1716/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>37009</start>
<end>37027</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Detection to Understanding: Multi-Turn Reasoning for Video Misinformation Analysis
%A Zeng, Zhi
%A Wu, Jiaying
%A Luo, Minnan
%A Zhang, Di
%A Yang, Yifei
%A Kong, Xiangzheng
%A Wan, Herun
%A Ma, Zihan
%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 zeng-etal-2026-detection
%X Video misinformation detection is often approached as a binary veracity classification problem, overlooking the complex reasoning required to explain how and why content misleads. Existing benchmarks fail to capture the diversity of manipulation strategies, such as AI-generated edits and out-of-context manipulation, and do not evaluate whether models can provide process-level justifications for their judgments. We address these limitations with MisVideoQA, a multi-turn benchmark designed to assess comprehensive understanding and reasoning in video misinformation analysis. MisVideoQA covers 12 fine-grained deception categories and evaluates models along six dimensions, progressing from perceptual attribution to intent and persuasion analysis. Recognizing that standard MLLMs struggle to sustain such structured, evidence-based deduction, we propose MisAgent, a Delphi-inspired multi-agent framework in which specialized agents collaboratively integrate multimodal cues with external evidence. Experimental results show that state-of-the-art multimodal large language models perform poorly on MisVideoQA, while MisAgent consistently improves reasoning accuracy and explanation quality. Together, our benchmark and framework establish a unified foundation for reliable, interpretable, and evidence-grounded video misinformation analysis.
%U https://aclanthology.org/2026.acl-long.1716/
%P 37009-37027
Markdown (Informal)
[From Detection to Understanding: Multi-Turn Reasoning for Video Misinformation Analysis](https://aclanthology.org/2026.acl-long.1716/) (Zeng et al., ACL 2026)
ACL
- Zhi Zeng, Jiaying Wu, Minnan Luo, Di Zhang, Yifei Yang, Xiangzheng Kong, Herun Wan, and Zihan Ma. 2026. From Detection to Understanding: Multi-Turn Reasoning for Video Misinformation Analysis. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 37009–37027, San Diego, California, United States. Association for Computational Linguistics.