@inproceedings{emerson-etal-2025-automated,
    title = "Automated Evaluation of Standardized Patients with {LLM}s",
    author = "Emerson, Andrew  and
      Ha, Le An  and
      Evanini, Keelan  and
      Somay, Su  and
      Frome, Kevin  and
      Harik, Polina  and
      Yaneva, Victoria",
    editor = "Wilson, Joshua  and
      Ormerod, Christopher  and
      Beiting Parrish, Magdalen",
    booktitle = "Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers",
    month = oct,
    year = "2025",
    address = "Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States",
    publisher = "National Council on Measurement in Education (NCME)",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.aimecon-main.25/",
    pages = "231--238",
    ISBN = "979-8-218-84228-4",
    abstract = "Standardized patients (SPs) are essential for clinical reasoning assessments in medical education. This paper introduces evaluation metrics that apply to both human and simulated SP systems. The metrics are computed using two LLM-as-a-judge approaches that align with human evaluators on SP performance, enabling scalable formative clinical reasoning assessments."
}