mdok-style at SemEval-2026 Task 9: Finetuning LLMs for Multilingual

Macko, D., Debnath, A.,¹ Simko, J.

SemEval-2026 Task 9 is focused on multilingual polarization detection. Specifically, it covers the identification of multilingual, multicultural and multievent polarization along three axes (in subtasks), namely detection, type, and manifestation. Online polarization presents a concern, because it is often followed by hate speech, offensive discourse, and social fragmentation. Therefore, its detection before it escalates is crucial for a safer and more inclusive online space. We have coped with this SemEval task by finetuning mid-size LLMs for the sequence-classification task using the QLoRA parameter-efficient finetuning technique. The training data augmented the multilingual (22 languages) training sets by anonymized, lower-cased, upper-cased, and homoglyphied counterparts, making the detection more robust.

Cite: Dominik Macko, Alok Debnath, and Jakub Simko. 2026. mdok-style at SemEval-2026 Task 9: Finetuning LLMs for Multilingual Polarization Detection. In Proceedings of the 20th International Workshop on Semantic Evaluation (2026), pages 314–321, San Diego, California, USA. Association for Computational Linguistics.