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
Year: 2026
Type: conference-paper
Abstract: The POLAR dataset contains various social media texts that might be polarized (conflictinducing 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 languagespecific small language models and compare our approach with state-of-the-art large language models on the POLAR dataset.By finetuning 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 1 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.
Institution: The University of Western Australia
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166799038