MKJ at SemEval-2026 Task 9: A Comparative Study of Generalist, Specialist, and Ensemble Strategies for Multilingual Polarization

Abstract: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: this https URL.

9 pages, 9 tables. Published in Proceedings of the 20th International Workshop on Semantic Evaluation (SemEval-2026), Task 9

Computation and Language (cs.CL); Computers and Society (cs.CY)

arXiv:2604.21370 [cs.CL]

(or arXiv:2604.21370v2 [cs.CL] for this version)

Proceedings of the 20th International Workshop on Semantic Evaluation (SemEval-2026), pages 1398-1406, San Diego, California, USA, July 2026. Association for Computational Linguistics

https://doi.org/10.18653/v1/2026.semeval-1.181 DOI(s) linking to related resources