@inproceedings{durand-etal-2026-pfr821,
    title = "pfr821 at {S}em{E}val-2026 Task 9: Multilingual Polarization Detection via Hybrid {XLM}-{R}o{BERT}a with Targeted Data Augmentation and Imbalance-Aware Training",
    author = "Durand, Antoine  and
      Hamon, R{\'e}mi  and
      Pereira, Matthieu  and
      Boucneau, Nathan  and
      Cintra, Paul  and
      Gadek, Guillaume  and
      Lefebvre, Louis  and
      Labeau, Matthieu",
    editor = "Kochmar, Ekaterina  and
      Ghosh, Debanjan  and
      North, Kai  and
      Komachi, Mamoru",
    booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/corrections-2026-07/2026.semeval-1.160/",
    doi = "10.18653/v1/2026.semeval-1.160",
    pages = "1169--1174",
    ISBN = "979-8-89176-414-9",
    abstract = "This paper describes HYPOLDET, the system submitted by team pfr821 to SemEval-2026 Task 9 (Polarization Detection, Subtask 1), a binary classification task over 22 typologically diverse languages. Our approach combines three complementary contributions. We first extend XLM-RoBERTa-Large with a custom transformer encoder layer and a learned attention-based pooling mechanism (Hybrid Architecture), allowing the model to aggregate token-level signals beyond the [CLS] representation. We then augment training data through a targeted LLM-based synthetic generation pipeline (Grok API), producing culturally grounded examples for low-resource and imbalanced languages. Finally, we address class imbalance at the training level through an imbalance-aware regime combining a per-language balanced batch sampler, weighted focal loss, and label smoothing. Our best single model achieves an unweighted macro-averaged F1 of 0.796, and a lightweight ensemble reaches 0.798, ranking in the top 10 for 7 languages and 2nd place for Hausa."
}