@inproceedings{hou-etal-2025-llm,
    title = "{LLM}-Human Alignment in Evaluating Teacher Questioning Practices: Beyond Ratings to Explanation",
    author = {Hou, Ruikun  and
      F{\"u}tterer, Tim  and
      B{\"u}hler, Babette  and
      Schreyer, Patrick  and
      Gerjets, Peter  and
      Trautwein, Ulrich  and
      Kasneci, Enkelejda},
    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.26/",
    pages = "239--249",
    ISBN = "979-8-218-84228-4",
    abstract = "This study investigates the alignment between large language models (LLMs) and human raters in assessing teacher questioning practices, moving beyond rating agreement to the evidence selected to justify their decisions. Findings highlight LLMs' potential to support large-scale classroom observation through interpretable, evidence-based scoring, with possible implications for concrete teacher feedback."
}