@inproceedings{li-etal-2025-towards-reliable,
    title = "Towards Reliable Generation of Clinical Chart Items: A Counterfactual Reasoning Approach with Large Language Models",
    author = "Li, Jiaxuan  and
      Rezayi, Saed  and
      Baldwin, Peter  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.16/",
    pages = "142--153",
    ISBN = "979-8-218-84228-4",
    abstract = "This study explores GPT-4 for generating clinical chart items in medical education using three prompting strategies. Expert evaluations found many items usable or promising. The counterfactual approach enhanced novelty, and item quality improved with high-surprisal examples. This is the first investigation of LLMs for automated clinical chart item generation."
}