@inproceedings{demirkaya-etal-2025-simulating,
    title = "Simulating Rating Scale Responses with {LLM}s for Early-Stage Item Evaluation",
    author = "Demirkaya, Onur  and
      Wei, Hsin-Ro  and
      Johnson, Evelyn",
    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/name-variant-enfa-fane/2025.aimecon-main.41/",
    pages = "385--392",
    ISBN = "979-8-218-84228-4",
    abstract = "This study explores the use of large language models to simulate human responses to Likert-scale items. A DeBERTa-base model fine-tuned with item text and examinee ability emulates a graded response model (GRM). High alignment with GRM probabilities and reasonable threshold recovery support LLMs as scalable tools for early-stage item evaluation."
}