@inproceedings{kodati-lakkireddy-2025-identifying,
title = "Identifying Contextual Triggers in Hate Speech Texts Using Explainable Large Language Models",
author = "Kodati, Dheeraj and
Lakkireddy, Bhuvana Sree",
editor = "Das, Sudhansu Bala and
Mishra, Pruthwik and
Singh, Alok and
Muhammad, Shamsuddeen Hassan and
Ekbal, Asif and
Das, Uday Kumar",
booktitle = "Proceedings of the Workshop on Beyond English: Natural Language Processing for all Languages in an Era of Large Language Models",
month = sep,
year = "2025",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, BULGARIA",
url = "https://aclanthology.org/2025.globalnlp-1.7/",
pages = "51--58",
abstract = "The pervasive spread of hate speech on online platforms poses a significant threat to social harmony, necessitating not only high-performing classifiers but also models capable of transparent, fine-grained interpretability. Existing methods often neglect the identification of influential contextual words that drive hate speech classification, limiting their reliability in high-stakes applications. To address this, we propose LLM-BiMACNet (Large Language Model-based Bidirectional Multi-Channel Attention Classification Network), an explainability-focused architecture that leverages pretrained language models and supervised attention to highlight key lexical indicators of hateful and offensive intent. Trained and evaluated on the HateXplain benchmark{---}comprising class labels, target community annotations, and human-labeled rationales{---}LLM-BiMACNet is optimized to simultaneously enhance both predictive performance and rationale alignment. Experimental results demonstrate that our model outperforms existing state-of-the-art approaches, achieving an accuracy of 87.3 {\%}, AUROC of 0.881, token-level F1 of 0.553, IOU-F1 of 0.261, AUPRC of 0.874, and comprehensiveness of 0.524, thereby offering highly interpretable and accurate hate speech detection."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kodati-lakkireddy-2025-identifying">
<titleInfo>
<title>Identifying Contextual Triggers in Hate Speech Texts Using Explainable Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dheeraj</namePart>
<namePart type="family">Kodati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bhuvana</namePart>
<namePart type="given">Sree</namePart>
<namePart type="family">Lakkireddy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Beyond English: Natural Language Processing for all Languages in an Era of Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sudhansu</namePart>
<namePart type="given">Bala</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pruthwik</namePart>
<namePart type="family">Mishra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alok</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shamsuddeen</namePart>
<namePart type="given">Hassan</namePart>
<namePart type="family">Muhammad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Uday</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, BULGARIA</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The pervasive spread of hate speech on online platforms poses a significant threat to social harmony, necessitating not only high-performing classifiers but also models capable of transparent, fine-grained interpretability. Existing methods often neglect the identification of influential contextual words that drive hate speech classification, limiting their reliability in high-stakes applications. To address this, we propose LLM-BiMACNet (Large Language Model-based Bidirectional Multi-Channel Attention Classification Network), an explainability-focused architecture that leverages pretrained language models and supervised attention to highlight key lexical indicators of hateful and offensive intent. Trained and evaluated on the HateXplain benchmark—comprising class labels, target community annotations, and human-labeled rationales—LLM-BiMACNet is optimized to simultaneously enhance both predictive performance and rationale alignment. Experimental results demonstrate that our model outperforms existing state-of-the-art approaches, achieving an accuracy of 87.3 %, AUROC of 0.881, token-level F1 of 0.553, IOU-F1 of 0.261, AUPRC of 0.874, and comprehensiveness of 0.524, thereby offering highly interpretable and accurate hate speech detection.</abstract>
<identifier type="citekey">kodati-lakkireddy-2025-identifying</identifier>
<location>
<url>https://aclanthology.org/2025.globalnlp-1.7/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>51</start>
<end>58</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Identifying Contextual Triggers in Hate Speech Texts Using Explainable Large Language Models
%A Kodati, Dheeraj
%A Lakkireddy, Bhuvana Sree
%Y Das, Sudhansu Bala
%Y Mishra, Pruthwik
%Y Singh, Alok
%Y Muhammad, Shamsuddeen Hassan
%Y Ekbal, Asif
%Y Das, Uday Kumar
%S Proceedings of the Workshop on Beyond English: Natural Language Processing for all Languages in an Era of Large Language Models
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, BULGARIA
%C Varna, Bulgaria
%F kodati-lakkireddy-2025-identifying
%X The pervasive spread of hate speech on online platforms poses a significant threat to social harmony, necessitating not only high-performing classifiers but also models capable of transparent, fine-grained interpretability. Existing methods often neglect the identification of influential contextual words that drive hate speech classification, limiting their reliability in high-stakes applications. To address this, we propose LLM-BiMACNet (Large Language Model-based Bidirectional Multi-Channel Attention Classification Network), an explainability-focused architecture that leverages pretrained language models and supervised attention to highlight key lexical indicators of hateful and offensive intent. Trained and evaluated on the HateXplain benchmark—comprising class labels, target community annotations, and human-labeled rationales—LLM-BiMACNet is optimized to simultaneously enhance both predictive performance and rationale alignment. Experimental results demonstrate that our model outperforms existing state-of-the-art approaches, achieving an accuracy of 87.3 %, AUROC of 0.881, token-level F1 of 0.553, IOU-F1 of 0.261, AUPRC of 0.874, and comprehensiveness of 0.524, thereby offering highly interpretable and accurate hate speech detection.
%U https://aclanthology.org/2025.globalnlp-1.7/
%P 51-58
Markdown (Informal)
[Identifying Contextual Triggers in Hate Speech Texts Using Explainable Large Language Models](https://aclanthology.org/2025.globalnlp-1.7/) (Kodati & Lakkireddy, GlobalNLP 2025)
ACL