@inproceedings{jha-etal-2024-memeguard,
title = "{M}eme{G}uard: An {LLM} and {VLM}-based Framework for Advancing Content Moderation via Meme Intervention",
author = "Jha, Prince and
Jain, Raghav and
Mandal, Konika and
Chadha, Aman and
Saha, Sriparna and
Bhattacharyya, Pushpak",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.luhme-long.439/",
doi = "10.18653/v1/2024.acl-long.439",
pages = "8084--8104",
abstract = "In the digital world, memes present a unique challenge for content moderation due to their potential to spread harmful content. Although detection methods have improved, proactive solutions such as intervention are still limited, with current research focusing mostly on text-based content, neglecting the widespread influence of multimodal content like memes. Addressing this gap, we present \textit{MemeGuard}, a comprehensive framework leveraging Large Language Models (LLMs) and Visual Language Models (VLMs) for meme intervention. \textit{MemeGuard} harnesses a specially fine-tuned VLM, \textit{VLMeme}, for meme interpretation, and a multimodal knowledge selection and ranking mechanism (\textit{MKS}) for distilling relevant knowledge. This knowledge is then employed by a general-purpose LLM to generate contextually appropriate interventions. Another key contribution of this work is the \textit{ \textbf{I}ntervening} \textit{ \textbf{C}yberbullying in \textbf{M}ultimodal \textbf{M}emes (ICMM)} dataset, a high-quality, labeled dataset featuring toxic memes and their corresponding human-annotated interventions. We leverage \textit{ICMM} to test \textit{MemeGuard}, demonstrating its proficiency in generating relevant and effective responses to toxic memes. red \textbf{Disclaimer}: \textit{This paper contains harmful content that may be disturbing to some readers.}"
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jha-etal-2024-memeguard">
<titleInfo>
<title>MemeGuard: An LLM and VLM-based Framework for Advancing Content Moderation via Meme Intervention</title>
</titleInfo>
<name type="personal">
<namePart type="given">Prince</namePart>
<namePart type="family">Jha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raghav</namePart>
<namePart type="family">Jain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Konika</namePart>
<namePart type="family">Mandal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aman</namePart>
<namePart type="family">Chadha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sriparna</namePart>
<namePart type="family">Saha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In the digital world, memes present a unique challenge for content moderation due to their potential to spread harmful content. Although detection methods have improved, proactive solutions such as intervention are still limited, with current research focusing mostly on text-based content, neglecting the widespread influence of multimodal content like memes. Addressing this gap, we present MemeGuard, a comprehensive framework leveraging Large Language Models (LLMs) and Visual Language Models (VLMs) for meme intervention. MemeGuard harnesses a specially fine-tuned VLM, VLMeme, for meme interpretation, and a multimodal knowledge selection and ranking mechanism (MKS) for distilling relevant knowledge. This knowledge is then employed by a general-purpose LLM to generate contextually appropriate interventions. Another key contribution of this work is the Intervening Cyberbullying in Multimodal Memes (ICMM) dataset, a high-quality, labeled dataset featuring toxic memes and their corresponding human-annotated interventions. We leverage ICMM to test MemeGuard, demonstrating its proficiency in generating relevant and effective responses to toxic memes. red Disclaimer: This paper contains harmful content that may be disturbing to some readers.</abstract>
<identifier type="citekey">jha-etal-2024-memeguard</identifier>
<identifier type="doi">10.18653/v1/2024.acl-long.439</identifier>
<location>
<url>https://aclanthology.org/2024.luhme-long.439/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>8084</start>
<end>8104</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MemeGuard: An LLM and VLM-based Framework for Advancing Content Moderation via Meme Intervention
%A Jha, Prince
%A Jain, Raghav
%A Mandal, Konika
%A Chadha, Aman
%A Saha, Sriparna
%A Bhattacharyya, Pushpak
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F jha-etal-2024-memeguard
%X In the digital world, memes present a unique challenge for content moderation due to their potential to spread harmful content. Although detection methods have improved, proactive solutions such as intervention are still limited, with current research focusing mostly on text-based content, neglecting the widespread influence of multimodal content like memes. Addressing this gap, we present MemeGuard, a comprehensive framework leveraging Large Language Models (LLMs) and Visual Language Models (VLMs) for meme intervention. MemeGuard harnesses a specially fine-tuned VLM, VLMeme, for meme interpretation, and a multimodal knowledge selection and ranking mechanism (MKS) for distilling relevant knowledge. This knowledge is then employed by a general-purpose LLM to generate contextually appropriate interventions. Another key contribution of this work is the Intervening Cyberbullying in Multimodal Memes (ICMM) dataset, a high-quality, labeled dataset featuring toxic memes and their corresponding human-annotated interventions. We leverage ICMM to test MemeGuard, demonstrating its proficiency in generating relevant and effective responses to toxic memes. red Disclaimer: This paper contains harmful content that may be disturbing to some readers.
%R 10.18653/v1/2024.acl-long.439
%U https://aclanthology.org/2024.luhme-long.439/
%U https://doi.org/10.18653/v1/2024.acl-long.439
%P 8084-8104
Markdown (Informal)
[MemeGuard: An LLM and VLM-based Framework for Advancing Content Moderation via Meme Intervention](https://aclanthology.org/2024.luhme-long.439/) (Jha et al., ACL 2024)
ACL