@inproceedings{agarwal-etal-2025-cogstack,
    title = "{C}og{S}tack-{KCL}-{UCL} at {A}rch{EHR}-{QA} 2025: Investigating Hybrid {LLM} Approaches for Grounded Clinical Question Answering",
    author = "Agarwal, Shubham  and
      Searle, Thomas  and
      Noor, Kawsar  and
      Dobson, Richard",
    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.16/",
    pages = "126--135",
    ISBN = "979-8-89176-276-3",
    abstract = "We present our system for the ArchEHR shared task, which focuses on answering clinical and patient-facing questions grounded in real-world EHR data. Our core contribution is a 2-Stage prompting pipeline that separates evidence selection from answer generation while employing in-context learning strategies. Our experimentation leveraged the open-weight Gemma-v3 family of models, with our best submission using the Gemma-12B model securing 5th place overall on the unseen test set. Through systematic experimentation, we demonstrate the effectiveness of task decomposition in improving both factual accuracy and answer relevance in grounded clinical question answering."
}