@inproceedings{sabhahit-etal-2026-nasimlab,
title = "{NASIML}ab at {S}em{E}val-2026 Task 9: A Comparative Analysis of Fine-Tuned Small Language Models vs. Generative Large Language Models for Multilingual Polarization Type Detection",
author = "Sabhahit, Neel and
Selvaganapathy, Sanjeevan and
Nasim, Mehwish",
editor = "Kochmar, Ekaterina and
Ghosh, Debanjan and
North, Kai and
Komachi, Mamoru",
booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.semeval-1.413/",
pages = "3316--3327",
ISBN = "979-8-89176-414-9",
abstract = "The POLAR dataset contains various social media texts that might be polarized (conflict-inducing or dangerously divisive). The task at hand is to identify whether any of the following types of polarization are present: political, racial/ethnic, religious, gender/sexual, and other types across 22 languages. In this paper, we propose a system of fine-tuned language-specific small language models and compare our approach with state-of-the-art large language models on the POLAR dataset. By fine-tuning models for each language, we demonstrate that fine-tuned small encoder-only models consistently outperform large language models, especially for low-resource languages. Our system performs well on this task for most low-resource languages, notably taking the top spot on the leaderboard in Burmese (mya), appearing within the top 10 for 12 languages, and within the top 20 for all remaining languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sabhahit-etal-2026-nasimlab">
<titleInfo>
<title>NASIMLab at SemEval-2026 Task 9: A Comparative Analysis of Fine-Tuned Small Language Models vs. Generative Large Language Models for Multilingual Polarization Type Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Neel</namePart>
<namePart type="family">Sabhahit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanjeevan</namePart>
<namePart type="family">Selvaganapathy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mehwish</namePart>
<namePart type="family">Nasim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Workshop on Semantic Evaluation (2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debanjan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">North</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mamoru</namePart>
<namePart type="family">Komachi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-414-9</identifier>
</relatedItem>
<abstract>The POLAR dataset contains various social media texts that might be polarized (conflict-inducing or dangerously divisive). The task at hand is to identify whether any of the following types of polarization are present: political, racial/ethnic, religious, gender/sexual, and other types across 22 languages. In this paper, we propose a system of fine-tuned language-specific small language models and compare our approach with state-of-the-art large language models on the POLAR dataset. By fine-tuning models for each language, we demonstrate that fine-tuned small encoder-only models consistently outperform large language models, especially for low-resource languages. Our system performs well on this task for most low-resource languages, notably taking the top spot on the leaderboard in Burmese (mya), appearing within the top 10 for 12 languages, and within the top 20 for all remaining languages.</abstract>
<identifier type="citekey">sabhahit-etal-2026-nasimlab</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.413/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>3316</start>
<end>3327</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NASIMLab at SemEval-2026 Task 9: A Comparative Analysis of Fine-Tuned Small Language Models vs. Generative Large Language Models for Multilingual Polarization Type Detection
%A Sabhahit, Neel
%A Selvaganapathy, Sanjeevan
%A Nasim, Mehwish
%Y Kochmar, Ekaterina
%Y Ghosh, Debanjan
%Y North, Kai
%Y Komachi, Mamoru
%S Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-414-9
%F sabhahit-etal-2026-nasimlab
%X The POLAR dataset contains various social media texts that might be polarized (conflict-inducing or dangerously divisive). The task at hand is to identify whether any of the following types of polarization are present: political, racial/ethnic, religious, gender/sexual, and other types across 22 languages. In this paper, we propose a system of fine-tuned language-specific small language models and compare our approach with state-of-the-art large language models on the POLAR dataset. By fine-tuning models for each language, we demonstrate that fine-tuned small encoder-only models consistently outperform large language models, especially for low-resource languages. Our system performs well on this task for most low-resource languages, notably taking the top spot on the leaderboard in Burmese (mya), appearing within the top 10 for 12 languages, and within the top 20 for all remaining languages.
%U https://aclanthology.org/2026.semeval-1.413/
%P 3316-3327
Markdown (Informal)
[NASIMLab at SemEval-2026 Task 9: A Comparative Analysis of Fine-Tuned Small Language Models vs. Generative Large Language Models for Multilingual Polarization Type Detection](https://aclanthology.org/2026.semeval-1.413/) (Sabhahit et al., SemEval 2026)
ACL