@inproceedings{baldwin-2025-implicit,
    title = "Implicit Biases in Large Vision{--}Language Models in Classroom Contexts",
    author = "Baldwin, Peter",
    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.26/",
    pages = "211--217",
    ISBN = "979-8-218-84229-1",
    abstract = "Using a counterfactual, adversarial, audit-style approach, we tested whether ChatGPT-4o evaluates classroom lectures differently based on teacher demographics. The model was told only to rate lecture excerpts embedded within classroom images{---}without reference to the images themselves. Despite this, ratings varied systematically by teacher race and sex, revealing implicit bias."
}