@inproceedings{gao-etal-2026-llms-judge,
    title = "Can {LLM}s Judge Pedagogy? Assessing Conversational {AI} {STEM} Tutoring with {AI}-as-a-Judge",
    author = "Gao, Xintian  and
      Shen, Qian  and
      Li, Xin",
    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 = "2026",
    address = "Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States",
    publisher = "National Council on Measurement in Education (NCME)",
    url = "https://aclanthology.org/2026.aimecon-main.69/",
    pages = "612--621",
    ISBN = "979-8-9983004-0-0"
}