@inproceedings{purbey-etal-2025-1-800,
title = "1-800-{SHARED}-{TASKS}@{NLU} of {D}evanagari Script Languages 2025: Detection of Language, Hate Speech, and Targets using {LLM}s",
author = "Purbey, Jebish and
Pullakhandam, Siddartha and
Mehreen, Kanwal and
Arham, Muhammad and
Sharma, Drishti and
Srivastava, Ashay and
Kadiyala, Ram Mohan Rao",
editor = "Sarveswaran, Kengatharaiyer and
Vaidya, Ashwini and
Krishna Bal, Bal and
Shams, Sana and
Thapa, Surendrabikram",
booktitle = "Proceedings of the First Workshop on Challenges in Processing South Asian Languages (CHiPSAL 2025)",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2025.chipsal-1.23/",
pages = "223--235",
abstract = "This paper presents a detailed system description of our entry for the CHiPSAL 2025 challenge, focusing on language detection, hate speech identification, and target detection in Devanagari script languages. We experimented with a combination of large language models and their ensembles, including MuRIL, IndicBERT, and Gemma-2, and leveraged unique techniques like focal loss to address challenges in the natural understanding of Devanagari languages, such as multilingual processing and class imbalance. Our approach achieved competitive results across all tasks: F1 of 0.9980, 0.7652, and 0.6804 for Sub-tasks A, B, and C respectively. This work provides insights into the effectiveness of transformer models in tasks with domain-specific and linguistic challenges, as well as areas for potential improvement in future iterations."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="purbey-etal-2025-1-800">
<titleInfo>
<title>1-800-SHARED-TASKS@NLU of Devanagari Script Languages 2025: Detection of Language, Hate Speech, and Targets using LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jebish</namePart>
<namePart type="family">Purbey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siddartha</namePart>
<namePart type="family">Pullakhandam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kanwal</namePart>
<namePart type="family">Mehreen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Arham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Drishti</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashay</namePart>
<namePart type="family">Srivastava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ram</namePart>
<namePart type="given">Mohan</namePart>
<namePart type="given">Rao</namePart>
<namePart type="family">Kadiyala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Challenges in Processing South Asian Languages (CHiPSAL 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kengatharaiyer</namePart>
<namePart type="family">Sarveswaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashwini</namePart>
<namePart type="family">Vaidya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bal</namePart>
<namePart type="family">Krishna Bal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sana</namePart>
<namePart type="family">Shams</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Surendrabikram</namePart>
<namePart type="family">Thapa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents a detailed system description of our entry for the CHiPSAL 2025 challenge, focusing on language detection, hate speech identification, and target detection in Devanagari script languages. We experimented with a combination of large language models and their ensembles, including MuRIL, IndicBERT, and Gemma-2, and leveraged unique techniques like focal loss to address challenges in the natural understanding of Devanagari languages, such as multilingual processing and class imbalance. Our approach achieved competitive results across all tasks: F1 of 0.9980, 0.7652, and 0.6804 for Sub-tasks A, B, and C respectively. This work provides insights into the effectiveness of transformer models in tasks with domain-specific and linguistic challenges, as well as areas for potential improvement in future iterations.</abstract>
<identifier type="citekey">purbey-etal-2025-1-800</identifier>
<location>
<url>https://aclanthology.org/2025.chipsal-1.23/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>223</start>
<end>235</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T 1-800-SHARED-TASKS@NLU of Devanagari Script Languages 2025: Detection of Language, Hate Speech, and Targets using LLMs
%A Purbey, Jebish
%A Pullakhandam, Siddartha
%A Mehreen, Kanwal
%A Arham, Muhammad
%A Sharma, Drishti
%A Srivastava, Ashay
%A Kadiyala, Ram Mohan Rao
%Y Sarveswaran, Kengatharaiyer
%Y Vaidya, Ashwini
%Y Krishna Bal, Bal
%Y Shams, Sana
%Y Thapa, Surendrabikram
%S Proceedings of the First Workshop on Challenges in Processing South Asian Languages (CHiPSAL 2025)
%D 2025
%8 January
%I International Committee on Computational Linguistics
%C Abu Dhabi, UAE
%F purbey-etal-2025-1-800
%X This paper presents a detailed system description of our entry for the CHiPSAL 2025 challenge, focusing on language detection, hate speech identification, and target detection in Devanagari script languages. We experimented with a combination of large language models and their ensembles, including MuRIL, IndicBERT, and Gemma-2, and leveraged unique techniques like focal loss to address challenges in the natural understanding of Devanagari languages, such as multilingual processing and class imbalance. Our approach achieved competitive results across all tasks: F1 of 0.9980, 0.7652, and 0.6804 for Sub-tasks A, B, and C respectively. This work provides insights into the effectiveness of transformer models in tasks with domain-specific and linguistic challenges, as well as areas for potential improvement in future iterations.
%U https://aclanthology.org/2025.chipsal-1.23/
%P 223-235
Markdown (Informal)
[1-800-SHARED-TASKS@NLU of Devanagari Script Languages 2025: Detection of Language, Hate Speech, and Targets using LLMs](https://aclanthology.org/2025.chipsal-1.23/) (Purbey et al., CHiPSAL 2025)
ACL
- Jebish Purbey, Siddartha Pullakhandam, Kanwal Mehreen, Muhammad Arham, Drishti Sharma, Ashay Srivastava, and Ram Mohan Rao Kadiyala. 2025. 1-800-SHARED-TASKS@NLU of Devanagari Script Languages 2025: Detection of Language, Hate Speech, and Targets using LLMs. In Proceedings of the First Workshop on Challenges in Processing South Asian Languages (CHiPSAL 2025), pages 223–235, Abu Dhabi, UAE. International Committee on Computational Linguistics.