MKJ at SemEval-2026 Task 9: A Comparative Study of Generalist, Specialist, and Ensemble Strategies for Multilingual Polarization
Apr 13, 2026·
Maziar Kianimoghadam Jouneghani
University of Turin
·
0 min readAbstract
We present a systematic study of multilingual polarization detection across 22 languages for SemEval-2026 Task 9 (Subtask 1), contrasting multilingual generalists with language-specific specialists and hybrid ensembles. While a standard generalist like XLM-RoBERTa suffices when its tokenizer aligns with the target text, it may struggle with distinct scripts (e.g., Khmer, Odia) where monolingual specialists yield significant gains. Rather than enforcing a single universal architecture, we adopt a language-adaptive framework that switches between multilingual generalists, language-specific specialists, and hybrid ensembles based on development performance. Additionally, cross-lingual augmentation via NLLB-200 yielded mixed results, often underperforming native architecture selection and degrading morphologically rich tracks. Our final system achieves an overall macro-averaged F1 score of 0.796 and an average accuracy of 0.826 across all 22 tracks. Code and final test predictions are publicly available at: https://github.com/Maziarkiani/SemEval2026-Task9-Subtask1-Polarization.
Type
Publication
To appear in Proceedings of the 20th International Workshop on Semantic Evaluation (SemEval-2026)
Authors
NLP Researcher
I am an NLP and Computational Linguistics researcher currently pursuing my Master’s degree in Language Technologies and Digital Humanities at University of Turin. My academic focus is on Large Language Models (LLMs), Explainable AI (XAI), multilingual NLP, and Human-in-the-Loop AI (HITL).
Beyond academia, I have over 3 years of hands-on industry experience in SEO, web content, and data-driven digital marketing.
Research Interests:
- Explainable AI (XAI)
- In-Context Learning (ICL)
- Human-in-the-Loop AI (HITL)
- Information Disorder
- Multilingual & Cross-Cultural NLP