@inproceedings{balachandran-etal-2025-exl,
    title = "{EXL} Health {AI} Lab at {MEDIQA}-{OE} 2025: Evaluating Prompting Strategies with {M}ed{G}emma for Medical Order Extraction",
    author = "Balachandran, Abhinand  and
      Durgapraveen, Bavana  and
      Sudhagar, Gowsikkan Sikkan  and
      S, Vidhya Varshany J  and
      Rajkumar, Sriram",
    editor = "Ben Abacha, Asma  and
      Bethard, Steven  and
      Bitterman, Danielle  and
      Naumann, Tristan  and
      Roberts, Kirk",
    booktitle = "Proceedings of the 7th Clinical Natural Language Processing Workshop",
    month = oct,
    year = "2025",
    address = "Virtual",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/retractions/2025.clinicalnlp-1.8/",
    pages = "68--74",
    abstract = "The accurate extraction of medical orders fromdoctor-patient conversations is a critical taskfor reducing clinical documentation burdensand ensuring patient safety. This paper detailsour team{'}s submission to the MEDIQA-OE-2025Shared Task. We investigate the performanceof MedGemma, a new domain-specific opensource language model, for structured order extraction. We systematically evaluate three distinct prompting paradigms: a straightforwardone-shot approach, a reasoning-focused ReActframework, and a multi-step agentic workflow.Our experiments reveal that while more complex frameworks like ReAct and agentic flowsare powerful, the simpler one-shot promptingmethod achieved the highest performance onthe official validation set. We posit that on manually annotated transcripts, complex reasoningchains can lead to ``overthinking'' and introduce noise, making a direct approach more robust and efficient. Our work provides valuableinsights into selecting appropriate promptingstrategies for clinical information extraction invaried data conditions."
}