@inproceedings{jing-etal-2025-hvguard,
title = "{HVG}uard: Utilizing Multimodal Large Language Models for Hateful Video Detection",
author = "Jing, Yiheng and
Zhang, Mingming and
Zhuang, Yong and
Guo, Jiacheng and
Wang, Juan and
Xu, Xiaoyang and
Yi, Wenzhe and
Guo, Keyan and
Hu, Hongxin",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.456/",
pages = "9004--9017",
ISBN = "979-8-89176-332-6",
abstract = "The rapid growth of video platforms has transformed information dissemination and led to an explosion of multimedia content. However, this widespread reach also introduces risks, as some users exploit these platforms to spread hate speech, which is often concealed through complex rhetoric, making hateful video detection a critical challenge. Existing detection methods rely heavily on unimodal analysis or simple feature fusion, struggling to capture cross-modal interactions and reason through implicit hate in sarcasm and metaphor. To address these limitations, we propose HVGuard, the first reasoning-based hateful video detection framework with multimodal large language models (MLLMs). Our approach integrates Chain-of-Thought (CoT) reasoning to enhance multimodal interaction modeling and implicit hate interpretation. Additionally, we design a Mixture-of-Experts (MoE) network for efficient multimodal fusion and final decision-making. The framework is modular and extensible, allowing flexible integration of different MLLMs and encoders. Experimental results demonstrate that HVGuard outperforms all existing advanced detection tools, achieving an improvement of 6.88{\%} to 13.13{\%} in accuracy and 9.21{\%} to 34.37{\%} in M-F1 on two public datasets covering both English and Chinese."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jing-etal-2025-hvguard">
<titleInfo>
<title>HVGuard: Utilizing Multimodal Large Language Models for Hateful Video Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yiheng</namePart>
<namePart type="family">Jing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingming</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yong</namePart>
<namePart type="family">Zhuang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiacheng</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoyang</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenzhe</namePart>
<namePart type="family">Yi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Keyan</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongxin</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>The rapid growth of video platforms has transformed information dissemination and led to an explosion of multimedia content. However, this widespread reach also introduces risks, as some users exploit these platforms to spread hate speech, which is often concealed through complex rhetoric, making hateful video detection a critical challenge. Existing detection methods rely heavily on unimodal analysis or simple feature fusion, struggling to capture cross-modal interactions and reason through implicit hate in sarcasm and metaphor. To address these limitations, we propose HVGuard, the first reasoning-based hateful video detection framework with multimodal large language models (MLLMs). Our approach integrates Chain-of-Thought (CoT) reasoning to enhance multimodal interaction modeling and implicit hate interpretation. Additionally, we design a Mixture-of-Experts (MoE) network for efficient multimodal fusion and final decision-making. The framework is modular and extensible, allowing flexible integration of different MLLMs and encoders. Experimental results demonstrate that HVGuard outperforms all existing advanced detection tools, achieving an improvement of 6.88% to 13.13% in accuracy and 9.21% to 34.37% in M-F1 on two public datasets covering both English and Chinese.</abstract>
<identifier type="citekey">jing-etal-2025-hvguard</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.456/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>9004</start>
<end>9017</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HVGuard: Utilizing Multimodal Large Language Models for Hateful Video Detection
%A Jing, Yiheng
%A Zhang, Mingming
%A Zhuang, Yong
%A Guo, Jiacheng
%A Wang, Juan
%A Xu, Xiaoyang
%A Yi, Wenzhe
%A Guo, Keyan
%A Hu, Hongxin
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F jing-etal-2025-hvguard
%X The rapid growth of video platforms has transformed information dissemination and led to an explosion of multimedia content. However, this widespread reach also introduces risks, as some users exploit these platforms to spread hate speech, which is often concealed through complex rhetoric, making hateful video detection a critical challenge. Existing detection methods rely heavily on unimodal analysis or simple feature fusion, struggling to capture cross-modal interactions and reason through implicit hate in sarcasm and metaphor. To address these limitations, we propose HVGuard, the first reasoning-based hateful video detection framework with multimodal large language models (MLLMs). Our approach integrates Chain-of-Thought (CoT) reasoning to enhance multimodal interaction modeling and implicit hate interpretation. Additionally, we design a Mixture-of-Experts (MoE) network for efficient multimodal fusion and final decision-making. The framework is modular and extensible, allowing flexible integration of different MLLMs and encoders. Experimental results demonstrate that HVGuard outperforms all existing advanced detection tools, achieving an improvement of 6.88% to 13.13% in accuracy and 9.21% to 34.37% in M-F1 on two public datasets covering both English and Chinese.
%U https://aclanthology.org/2025.emnlp-main.456/
%P 9004-9017
Markdown (Informal)
[HVGuard: Utilizing Multimodal Large Language Models for Hateful Video Detection](https://aclanthology.org/2025.emnlp-main.456/) (Jing et al., EMNLP 2025)
ACL
- Yiheng Jing, Mingming Zhang, Yong Zhuang, Jiacheng Guo, Juan Wang, Xiaoyang Xu, Wenzhe Yi, Keyan Guo, and Hongxin Hu. 2025. HVGuard: Utilizing Multimodal Large Language Models for Hateful Video Detection. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 9004–9017, Suzhou, China. Association for Computational Linguistics.