@inproceedings{huang-wilson-2025-evaluating,
    title = "Evaluating {LLM}-Based Automated Essay Scoring: Accuracy, Fairness, and Validity",
    author = "Huang, Yue  and
      Wilson, Joshua",
    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.9/",
    pages = "71--83",
    ISBN = "979-8-218-84229-1",
    abstract = "This study evaluates large language models (LLMs) for automated essay scoring (AES), comparing prompt strategies and fairness across student groups. We found that well-designed prompting helps LLMs approach traditional AES performance, but both differ from human scores for ELLs{---}the traditional model shows larger overrall gaps, while LLMs show subtler disparities."
}