@inproceedings{sachdeva-park-2025-leveraging,
    title = "Leveraging {LLM}s for Cognitive Skill Mapping in {TIMSS} Mathematics Assessment",
    author = "Sachdeva, Ruchi J  and
      Park, Jung Yeon",
    editor = "Wilson, Joshua  and
      Ormerod, Christopher  and
      Beiting Parrish, Magdalen",
    booktitle = "Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress",
    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-wip.28/",
    pages = "223--228",
    ISBN = "979-8-218-84229-1",
    abstract = "This study evaluates ChatGPT-4{'}s potential to support validation of Q-matrices and analysis of complex skill{--}item interactions. By comparing its outputs to expert benchmarks, we assess accuracy, consistency, and limitations, offering insights into how large language models can augment expert judgment in diagnostic assessment and cognitive skill mapping."
}