Leveraging LaBSE with Progressive Curriculum Learning for Multicultural Polarization
For researchers working on multilingual NLP tasks with limited data, this work offers a practical method to improve cross-lingual transfer, though the gains are modest and domain-specific.
The paper tackles multilingual online polarization detection under data scarcity, achieving up to 0.2 macro F1 improvement in low-resource languages by using LaBSE embeddings with progressive curriculum learning.
Detecting online polarization remains a critical challenge, particularly in multilingual and multicultural contexts 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 active area 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, to obtain strong cross-lingual learning which enhances scores in low-resource language by a score up to 0.2 macro F1. Furthermore, we provide a comprehensive ablation study evaluating the performance of diverse encoder models in the Qwen model family within a retrieval-based prompting framework. Our code will be soon available at https://github.com/carrycurious/PolarMind.