@inproceedings{ahuir-etal-2026-elirf,
    title = "{EL}i{RF}-{UPV}@{M}ed{E}x{ACT} 2026: Dynamic Section Conditioning for Medical Decision Span Detection in Discharge Summaries",
    author = "Ahuir, Vicent  and
      Hurtado, Llu{\'i}s  and
      Castro-Bleda, Mar{\'i}a",
    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-2.11/",
    pages = "71--76",
    ISBN = "979-8-89176-435-4",
    abstract = "Extracting medical decisions from discharge summaries is essential for downstream clinical analytics, yet the task remains challenging due to the heterogeneous structure of electronic health records. For the MedExACT track at ACL 2026, we proposed a system that achieved the 4th position. Our approach first applies dynamic section conditioning to capture the contextual dependencies inherent in each document. A transformer backbone is then augmented with category- and section-aware layer mixing, enabling us to fuse global document structure with fine-grained semantic cues. To further improve robustness, we employ an ensemble of instruction-tuned large language models for automatic section extraction, while a fairness-oriented model selection criterion ensures that performance does not degrade on minority demographic subgroups. The resulting system attains a final score of 0.5806 on the held-out test set and demonstrates significant gains over the baseline across all evaluated subpopulations."
}