@inproceedings{buns-etal-2025-wispermed,
    title = "{W}is{P}er{M}ed at {A}rch{EHR}-{QA} 2025: A Modular, Relevance-First Approach for Grounded Question Answering on Eletronic Health Records",
    author = {B{\"u}ns, Jan-Henning  and
      Damm, Hendrik  and
      Pakull, Tabea  and
      Nensa, Felix  and
      Livingstone, Elisabeth},
    editor = "Soni, Sarvesh  and
      Demner-Fushman, Dina",
    booktitle = "BioNLP 2025 Shared Tasks",
    month = aug,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/acl25-workshop-ingestion/2025.bionlp-share.5/",
    pages = "41--49",
    ISBN = "979-8-89176-276-3",
    abstract = "Automatically answering patient questions based on electronic health records (EHRs) requires systems that both identify relevant evidence and generate accurate, grounded responses. We present a three-part pipeline developed by WisPerMed for the ArchEHR-QA 2025 shared task. First, a fine-tuned BioClinicalBERT model classifies note sentences by their relevance using synonym-based and paraphrased data augmentation. Second, a constrained generation step uses DistilBART-MedSummary to produce faithful answers strictly limited to top-ranked evidence. Third, we align each answer sentence to its supporting evidence via BiomedBERT embeddings and ROUGE-based similarity scoring to ensure citation transparency. Our system achieved a 35.0{\%} overall score on the hidden test set, outperforming the organizer{'}s baseline by 4.3 percentage points. Gains in BERTScore (+44{\%}) and SARI (+119{\%}) highlight substantial improvements in semantic accuracy and relevance. This modular approach demonstrates that enforcing evidence-awareness and citation grounding enhances both answer quality and trustworthiness in clinical QA systems."
}