Detecting online polarization remains a critical challenge, particularly in multilingual and multicultural on texts where intergroup hostility is prevalent. The problem is particularly challenging due to the data scarcity for these tasks in the low-resource languages. Identifying such phenomena has become an activearea of research and is addressed in SemEval 2026 Task 9: Multilingual, Multicultural Online Polarization Detection. To address this problem we propose an architecture that leverages LaBSE embeddings—an unconventional choice typically reserved for retrieval tasks—toobtain strong cross-lingual learning which enhances scores in low-resource language by ascore up to 0.2 macro F1. Furthermore, we provide a comprehensive ablation study evaluatingthe performance of diverse encoder models in the Qwen model family within a retrieval-basedprompting framework.