@inproceedings{arora-2026-copol,
    title = "{C}o{P}ol at {S}em{E}val-2026 Task 9: Modeling Polarization Type Co-occurrence with Label Correlation Networks",
    author = "Arora, Pushkar",
    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/ingest-acl-workshops/2026.semeval-1.443/",
    pages = "3621--3627",
    ISBN = "979-8-89176-414-9",
    abstract = "POLAR-LDA is a label-dependency{--}aware system for SemEval-2026 Task 9 (multi-label polarization type classification) that augments an mDeBERTa-v3-base encoder with a Label Correlation Network (language-specific directed co-occurrence matrices + GAT), Asymmetric Loss tuned for extreme positive scarcity, and a language-grouped ensemble. The system scores 0.567 macro F1 across 22 languages (range 0.784 Hindi {---} 0.256 Italian) and shows clear ablation gains (ASL +0.041, LCN +0.030, ensemble +0.018). Key findings: absolute data voids (0{--}1 positive examples) form an unrecoverable floor for supervised learning; label co-occurrence is culturally situated (e.g., political{\ensuremath{\leftrightarrow}}religious in Indic vs. political{\ensuremath{\leftrightarrow}}racial in some Western languages) and benefits from language-specific graphs; and per-label training volume predicts cross-lingual performance better than linguistic family. Limitations are honest and important: noisy AL estimates under scarcity, an incoherent residual ``other'' category, and domain mismatch between pretraining corpora and polarization discourse. Overall, the paper offers a strong shared-task system and useful empirical diagnostics{---}practical and well-executed, but incrementally novel methodologicall"
}