@inproceedings{shields-menard-etal-2025-utsa,
    title = "{UTSA}-{NLP} at {A}rch{EHR}-{QA} 2025: Improving {EHR} Question Answering via Self-Consistency Prompting",
    author = "Shields-Menard, Sara  and
      Reimers, Zach  and
      Gardner, Joshua  and
      Perry, David  and
      Rios, Anthony",
    editor = "Soni, Sarvesh  and
      Demner-Fushman, Dina",
    booktitle = "Proceedings of the 24th Workshop on Biomedical Language Processing (Shared Tasks)",
    month = aug,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.bionlp-share.10/",
    doi = "10.18653/v1/2025.bionlp-share.10",
    pages = "81--90",
    ISBN = "979-8-89176-276-3",
    abstract = "We describe our system for the ArchEHR-QA Shared Task on answering clinical questions using electronic health records (EHRs). Our approach uses large language models in two steps: first, to find sentences in the EHR relevant to a clinician{'}s question, and second, to generate a short, citation-supported response based on those sentences. We use few-shot prompting, self-consistency, and thresholding to improve the sentence classification step to decide which sentences are essential. We compare several models and find that a smaller 8B model performs better than a larger 70B model for identifying relevant information. Our results show that accurate sentence selection is critical for generating high-quality responses and that self-consistency with thresholding helps make these decisions more reliable."
}