@inproceedings{afrin-etal-2025-toward,
    title = "Toward Automated Evaluation of {AI}-Generated Item Drafts in Clinical Assessment",
    author = "Afrin, Tazin  and
      Ha, Le An  and
      Yaneva, Victoria  and
      Evanini, Keelan  and
      Go, Steven  and
      DeRuchie, Kristine  and
      Heilig, Michael",
    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.19/",
    pages = "172--182",
    ISBN = "979-8-218-84228-4",
    abstract = "This study examines the classification of AI-generated clinical multiple-choice questions drafts as ``helpful'' or ``non-helpful'' starting points. Expert judgments were analyzed, and multiple classifiers were evaluated{---}including feature-based models, fine-tuned transformers, and few-shot prompting with GPT-4. Our findings highlight the challenges and considerations for evaluation methods of AI-generated items in clinical test development."
}