@inproceedings{baldwin-2025-using,
    title = "Using Generative {AI} to Develop a Common Metric in Item Response Theory",
    author = "Baldwin, Peter",
    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.30/",
    pages = "281--289",
    ISBN = "979-8-218-84228-4",
    abstract = "We propose a method for linking independently calibrated item response theory (IRT) scales using large language models to generate shared parameter estimates across forms. Applied to medical licensure data, the approach reliably recovers slope values across all conditions and yields accurate intercepts when cross-form differences in item difficulty are small."
}