@inproceedings{koontz-etal-2024-ixa,
    title = "Ixa-{M}ed at Discharge Me! Retrieval-Assisted Generation for Streamlining Discharge Documentation",
    author = "Koontz, Jordan C.  and
      Oronoz, Maite  and
      P{\'e}rez, Alicia",
    editor = "Demner-Fushman, Dina  and
      Ananiadou, Sophia  and
      Miwa, Makoto  and
      Roberts, Kirk  and
      Tsujii, Junichi",
    booktitle = "Proceedings of the 23rd Workshop on Biomedical Natural Language Processing",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.bionlp-1.57/",
    doi = "10.18653/v1/2024.bionlp-1.57",
    pages = "658--663",
    abstract = "In this paper we present our system for the BioNLP ACL`24 {\textquotedblleft}Discharge Me!{\textquotedblright} task on automating discharge summary section generation. Using Retrieval-Augmented Generation, we combine a Large Language Model (LLM) with external knowledge to guide the generation of the target sections. Our approach generates structured patient summaries from discharge notes using an instructed LLM, retrieves relevant {\textquotedblleft}Brief Hospital Course{\textquotedblright} and {\textquotedblleft}Discharge Instructions{\textquotedblright} examples via BM25 and SentenceBERT, and provides this context to a frozen LLM for generation. Our top system using SentenceBERT retrieval achieves an overall score of 0.183, outperforming zero-shot baselines. We analyze performance across different aspects, discussing limitations and future research directions."
}