In this paper, we present our system, which was submitted to SemEval-2026 Task 9 (Subtask 1: Polarization Detection) and focuses on binary classification of polarized content in Arabic social media text. To address Arabic linguistic variations, we propose a single-model approach that combines fine-tuned AraBERT with synonym-based data augmentation. On the Arabic bind set, our method achieves a competitive macro F1-score of 0.831 and an accuracy of 0.833. Among the 45 participating teams, our system ranked 11th overall, with a performance gap of 0.018 macro F1 from the top-ranked team (0.8488). The results show that a fine-tuned AraBERT with synonym replacement is a strong, simple, and reproducible baseline that outperforms more complex setups in dealing with Arabic attitude polarization nuances.

In this paper, we demonstrate the system submitted to the shared task of medical text classification in Arabic. We proposed a single-model approach based on fine-tuned LLM-based embedding combined with hierarchical classical classifiers, achieving a competitive macro F1-score of 0.46 on the blind test set. We explored various modeling strategies, including tree-based ensembles, LLM, and hierarchical correction for rare classes, highlighting the effectiveness of domain-specific fine-tuning in low-resource settings. The results demonstrate that a single fine-tuned Arabic BERT variant can serve as a strong baseline in extreme imbalance scenarios, outperforming more complex ensembles in simplicity and reproducibility.