@inproceedings{zeng-etal-2025-imol,
title = "{IMOL}: Incomplete-Modality-Tolerant Learning for Multi-Domain Fake News Video Detection",
author = "Zeng, Zhi and
Wu, Jiaying and
Luo, Minnan and
Wan, Herun and
Kong, Xiangzheng and
Ma, Zihan and
Dai, Guang and
Zheng, Qinghua",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.1494/",
doi = "10.18653/v1/2025.acl-long.1494",
pages = "30921--30933",
ISBN = "979-8-89176-251-0",
abstract = "While recent advances in fake news video detection have shown promising potential, existing approaches typically (1) focus on a specific domain (e.g., politics) and (2) assume the availability of multiple modalities, including video, audio, description texts, and related images. However, these methods struggle to generalize to real-world scenarios, where questionable information spans diverse domains and is often modality-incomplete due to factors such as upload degradation or missing metadata. To address these challenges, we introduce two real-world multi-domain news video benchmarks that reflect modality incompleteness and propose IMOL, an incomplete-modality-tolerant learning framework for multi-domain fake news video detection. Inspired by cognitive theories suggesting that humans infer missing modalities through cross-modal guidance and retrieve relevant knowledge from memory for reference, IMOL employs a hierarchical transferable information integration strategy. This consists of two key phases: (1) leveraging cross-modal consistency to reconstruct missing modalities and (2) refining sample-level transferable knowledge through cross-sample associative reasoning. Extensive experiments demonstrate that IMOL significantly enhances the performance and robustness of multi-domain fake news video detection while effectively generalizing to unseen domains under incomplete modality conditions."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zeng-etal-2025-imol">
<titleInfo>
<title>IMOL: Incomplete-Modality-Tolerant Learning for Multi-Domain Fake News Video Detection</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">Herun</namePart>
<namePart type="family">Wan</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">Zihan</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guang</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qinghua</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>While recent advances in fake news video detection have shown promising potential, existing approaches typically (1) focus on a specific domain (e.g., politics) and (2) assume the availability of multiple modalities, including video, audio, description texts, and related images. However, these methods struggle to generalize to real-world scenarios, where questionable information spans diverse domains and is often modality-incomplete due to factors such as upload degradation or missing metadata. To address these challenges, we introduce two real-world multi-domain news video benchmarks that reflect modality incompleteness and propose IMOL, an incomplete-modality-tolerant learning framework for multi-domain fake news video detection. Inspired by cognitive theories suggesting that humans infer missing modalities through cross-modal guidance and retrieve relevant knowledge from memory for reference, IMOL employs a hierarchical transferable information integration strategy. This consists of two key phases: (1) leveraging cross-modal consistency to reconstruct missing modalities and (2) refining sample-level transferable knowledge through cross-sample associative reasoning. Extensive experiments demonstrate that IMOL significantly enhances the performance and robustness of multi-domain fake news video detection while effectively generalizing to unseen domains under incomplete modality conditions.</abstract>
<identifier type="citekey">zeng-etal-2025-imol</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.1494</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.1494/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>30921</start>
<end>30933</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IMOL: Incomplete-Modality-Tolerant Learning for Multi-Domain Fake News Video Detection
%A Zeng, Zhi
%A Wu, Jiaying
%A Luo, Minnan
%A Wan, Herun
%A Kong, Xiangzheng
%A Ma, Zihan
%A Dai, Guang
%A Zheng, Qinghua
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F zeng-etal-2025-imol
%X While recent advances in fake news video detection have shown promising potential, existing approaches typically (1) focus on a specific domain (e.g., politics) and (2) assume the availability of multiple modalities, including video, audio, description texts, and related images. However, these methods struggle to generalize to real-world scenarios, where questionable information spans diverse domains and is often modality-incomplete due to factors such as upload degradation or missing metadata. To address these challenges, we introduce two real-world multi-domain news video benchmarks that reflect modality incompleteness and propose IMOL, an incomplete-modality-tolerant learning framework for multi-domain fake news video detection. Inspired by cognitive theories suggesting that humans infer missing modalities through cross-modal guidance and retrieve relevant knowledge from memory for reference, IMOL employs a hierarchical transferable information integration strategy. This consists of two key phases: (1) leveraging cross-modal consistency to reconstruct missing modalities and (2) refining sample-level transferable knowledge through cross-sample associative reasoning. Extensive experiments demonstrate that IMOL significantly enhances the performance and robustness of multi-domain fake news video detection while effectively generalizing to unseen domains under incomplete modality conditions.
%R 10.18653/v1/2025.acl-long.1494
%U https://aclanthology.org/2025.acl-long.1494/
%U https://doi.org/10.18653/v1/2025.acl-long.1494
%P 30921-30933
Markdown (Informal)
[IMOL: Incomplete-Modality-Tolerant Learning for Multi-Domain Fake News Video Detection](https://aclanthology.org/2025.acl-long.1494/) (Zeng et al., ACL 2025)
ACL
- Zhi Zeng, Jiaying Wu, Minnan Luo, Herun Wan, Xiangzheng Kong, Zihan Ma, Guang Dai, and Qinghua Zheng. 2025. IMOL: Incomplete-Modality-Tolerant Learning for Multi-Domain Fake News Video Detection. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 30921–30933, Vienna, Austria. Association for Computational Linguistics.