@inproceedings{bezirhan-von-davier-2025-ai,
    title = "{AI}-Based Classification of {TIMSS} Items for Framework Alignment",
    author = "Bezirhan, Ummugul  and
      von Davier, Matthias",
    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.15/",
    pages = "134--141",
    ISBN = "979-8-218-84228-4",
    abstract = "Large-scale assessments rely on expert panels to verify that test items align with prescribed frameworks, a labor-intensive process. This study evaluates the use of GPT-4o to classify TIMSS items to content domain, cognitive domain, and difficulty categories. Findings highlight the potential of language models to support scalable, framework-aligned item verification."
}