@inproceedings{kumari-etal-2025-memedetoxnet,
title = "{M}eme{D}etox{N}et: Balancing Toxicity Reduction and Context Preservation",
author = "Kumari, Gitanjali and
Solanki, Jitendra and
Ekbal, Asif",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.1286/",
doi = "10.18653/v1/2025.findings-acl.1286",
pages = "25076--25098",
ISBN = "979-8-89176-256-5",
abstract = "Toxic memes often spread harmful and offensive content and pose a significant challenge in online environments. In this paper, we present MemeDetoxNet, a robust framework designed to mitigate toxicity in memes by leveraging fine-tuned pre-trained models. Our approach utilizes the interpretability of CLIP (Contrastive Language-Image Pre-Training) to identify toxic elements within the visual and textual components of memes. Our objective is to automatically assess the immorality of toxic memes and transform them into morally acceptable alternatives by employing large language models (LLMs) to replace offensive text and blurring toxic regions in the image. As a result, we proposed MemeDetoxNet that has three main primitives: (1) detection of toxic memes, (2) localizing and highlighting toxic visual and textual attributes, and (3) manipulating the toxic content to create a morally acceptable alternative. Empirical evaluation on several publicly available meme datasets shows a reduction in toxicity by approximately 10-20{\%}. Both qualitative and quantitative analyses further demonstrate MemeDetoxNet{'}s superior performance in detoxifying memes compared to the other methods. These results underscore MemeDetoxNet{'}s potential as an effective tool for content moderation on online platforms."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kumari-etal-2025-memedetoxnet">
<titleInfo>
<title>MemeDetoxNet: Balancing Toxicity Reduction and Context Preservation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gitanjali</namePart>
<namePart type="family">Kumari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jitendra</namePart>
<namePart type="family">Solanki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</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>Findings of the Association for Computational Linguistics: ACL 2025</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">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>Toxic memes often spread harmful and offensive content and pose a significant challenge in online environments. In this paper, we present MemeDetoxNet, a robust framework designed to mitigate toxicity in memes by leveraging fine-tuned pre-trained models. Our approach utilizes the interpretability of CLIP (Contrastive Language-Image Pre-Training) to identify toxic elements within the visual and textual components of memes. Our objective is to automatically assess the immorality of toxic memes and transform them into morally acceptable alternatives by employing large language models (LLMs) to replace offensive text and blurring toxic regions in the image. As a result, we proposed MemeDetoxNet that has three main primitives: (1) detection of toxic memes, (2) localizing and highlighting toxic visual and textual attributes, and (3) manipulating the toxic content to create a morally acceptable alternative. Empirical evaluation on several publicly available meme datasets shows a reduction in toxicity by approximately 10-20%. Both qualitative and quantitative analyses further demonstrate MemeDetoxNet’s superior performance in detoxifying memes compared to the other methods. These results underscore MemeDetoxNet’s potential as an effective tool for content moderation on online platforms.</abstract>
<identifier type="citekey">kumari-etal-2025-memedetoxnet</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.1286</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.1286/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>25076</start>
<end>25098</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MemeDetoxNet: Balancing Toxicity Reduction and Context Preservation
%A Kumari, Gitanjali
%A Solanki, Jitendra
%A Ekbal, Asif
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F kumari-etal-2025-memedetoxnet
%X Toxic memes often spread harmful and offensive content and pose a significant challenge in online environments. In this paper, we present MemeDetoxNet, a robust framework designed to mitigate toxicity in memes by leveraging fine-tuned pre-trained models. Our approach utilizes the interpretability of CLIP (Contrastive Language-Image Pre-Training) to identify toxic elements within the visual and textual components of memes. Our objective is to automatically assess the immorality of toxic memes and transform them into morally acceptable alternatives by employing large language models (LLMs) to replace offensive text and blurring toxic regions in the image. As a result, we proposed MemeDetoxNet that has three main primitives: (1) detection of toxic memes, (2) localizing and highlighting toxic visual and textual attributes, and (3) manipulating the toxic content to create a morally acceptable alternative. Empirical evaluation on several publicly available meme datasets shows a reduction in toxicity by approximately 10-20%. Both qualitative and quantitative analyses further demonstrate MemeDetoxNet’s superior performance in detoxifying memes compared to the other methods. These results underscore MemeDetoxNet’s potential as an effective tool for content moderation on online platforms.
%R 10.18653/v1/2025.findings-acl.1286
%U https://aclanthology.org/2025.findings-acl.1286/
%U https://doi.org/10.18653/v1/2025.findings-acl.1286
%P 25076-25098
Markdown (Informal)
[MemeDetoxNet: Balancing Toxicity Reduction and Context Preservation](https://aclanthology.org/2025.findings-acl.1286/) (Kumari et al., Findings 2025)
ACL