@inproceedings{kondadadi-2026-diverse,
    title = "Diverse Transformer Ensemble with Majority Voting for Medical Decision Extraction at {M}ed{E}x{ACT} 2026",
    author = "Kondadadi, Rishik",
    editor = "Gupta, Deepak  and
      Demner-Fushman, Dina",
    booktitle = "Proceedings of the {B}io{NLP} 2026 (Shared Tasks)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.bionlp-2.13/",
    pages = "87--91",
    ISBN = "979-8-89176-435-4",
    abstract = "This paper describes our system for the MedEx-ACT 2026 shared task on extracting and classifying medical decisions from ICU discharge summaries. We frame the task as BIO token classification and train 25 diverse transformer models spanning 13 distinct architectures, including Longformer, DeBERTa, RoBERTa, BioBERT, SciBERT, and others. Each model is trained with category-aware oversampling, focal loss, and demographic-group-aware sampling to address class imbalance and promote fairness across patient subgroups. At inference time, we aggregate predictions via text-normalized majority voting, retaining spans agreed upon by at least 6 of 25 models. Our best submission achieves a final score of 0.5554 on the test set, demonstrating that a simple vote-based ensemble over architecturally diverse models outperforms more complex filtering approaches. We find that architectural diversity is a key driver of ensemble quality and that cross-validation is essential for reliable model selection on small clinical datasets."
}