@inproceedings{khullar-etal-2025-hateimgprompts,
title = "{H}ate{I}mg{P}rompts: Mitigating Generation of Images Spreading Hate Speech",
author = "Khullar, Vineet Kumar and
Velugubantla, Venkatesh and
Reddy Rella, Bhanu Prakash and
Mannava, Mohan Krishna and
Sathvik, Msvpj",
editor = {H{\"a}m{\"a}l{\"a}inen, Mika and
{\"O}hman, Emily and
Bizzoni, Yuri and
Miyagawa, So and
Alnajjar, Khalid},
booktitle = "Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities",
month = may,
year = "2025",
address = "Albuquerque, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.nlp4dh-1.53/",
doi = "10.18653/v1/2025.nlp4dh-1.53",
pages = "647--652",
ISBN = "979-8-89176-234-3",
abstract = "The emergence of artificial intelligence has proven beneficial to numerous organizations, particularly in its various applications for social welfare. One notable application lies in AI-driven image generation tools. These tools produce images based on provided prompts. While this technology holds potential for constructive use, it also carries the risk of being exploited for malicious purposes, such as propagating hate. To address this we propose a novel dataset ``HateImgPrompts''. We have benchmarked the dataset with the latest models including GPT-3.5, LLAMA 2, etc. The dataset consists of 9467 prompts and the accuracy of the classifier after finetuning of the dataset is around 81{\%}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="khullar-etal-2025-hateimgprompts">
<titleInfo>
<title>HateImgPrompts: Mitigating Generation of Images Spreading Hate Speech</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vineet</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Khullar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Venkatesh</namePart>
<namePart type="family">Velugubantla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bhanu</namePart>
<namePart type="given">Prakash</namePart>
<namePart type="family">Reddy Rella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohan</namePart>
<namePart type="given">Krishna</namePart>
<namePart type="family">Mannava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Msvpj</namePart>
<namePart type="family">Sathvik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mika</namePart>
<namePart type="family">Hämäläinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="family">Öhman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuri</namePart>
<namePart type="family">Bizzoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">So</namePart>
<namePart type="family">Miyagawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Alnajjar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-234-3</identifier>
</relatedItem>
<abstract>The emergence of artificial intelligence has proven beneficial to numerous organizations, particularly in its various applications for social welfare. One notable application lies in AI-driven image generation tools. These tools produce images based on provided prompts. While this technology holds potential for constructive use, it also carries the risk of being exploited for malicious purposes, such as propagating hate. To address this we propose a novel dataset “HateImgPrompts”. We have benchmarked the dataset with the latest models including GPT-3.5, LLAMA 2, etc. The dataset consists of 9467 prompts and the accuracy of the classifier after finetuning of the dataset is around 81%.</abstract>
<identifier type="citekey">khullar-etal-2025-hateimgprompts</identifier>
<identifier type="doi">10.18653/v1/2025.nlp4dh-1.53</identifier>
<location>
<url>https://aclanthology.org/2025.nlp4dh-1.53/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>647</start>
<end>652</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HateImgPrompts: Mitigating Generation of Images Spreading Hate Speech
%A Khullar, Vineet Kumar
%A Velugubantla, Venkatesh
%A Reddy Rella, Bhanu Prakash
%A Mannava, Mohan Krishna
%A Sathvik, Msvpj
%Y Hämäläinen, Mika
%Y Öhman, Emily
%Y Bizzoni, Yuri
%Y Miyagawa, So
%Y Alnajjar, Khalid
%S Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities
%D 2025
%8 May
%I Association for Computational Linguistics
%C Albuquerque, USA
%@ 979-8-89176-234-3
%F khullar-etal-2025-hateimgprompts
%X The emergence of artificial intelligence has proven beneficial to numerous organizations, particularly in its various applications for social welfare. One notable application lies in AI-driven image generation tools. These tools produce images based on provided prompts. While this technology holds potential for constructive use, it also carries the risk of being exploited for malicious purposes, such as propagating hate. To address this we propose a novel dataset “HateImgPrompts”. We have benchmarked the dataset with the latest models including GPT-3.5, LLAMA 2, etc. The dataset consists of 9467 prompts and the accuracy of the classifier after finetuning of the dataset is around 81%.
%R 10.18653/v1/2025.nlp4dh-1.53
%U https://aclanthology.org/2025.nlp4dh-1.53/
%U https://doi.org/10.18653/v1/2025.nlp4dh-1.53
%P 647-652
Markdown (Informal)
[HateImgPrompts: Mitigating Generation of Images Spreading Hate Speech](https://aclanthology.org/2025.nlp4dh-1.53/) (Khullar et al., NLP4DH 2025)
ACL
- Vineet Kumar Khullar, Venkatesh Velugubantla, Bhanu Prakash Reddy Rella, Mohan Krishna Mannava, and Msvpj Sathvik. 2025. HateImgPrompts: Mitigating Generation of Images Spreading Hate Speech. In Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities, pages 647–652, Albuquerque, USA. Association for Computational Linguistics.