@inproceedings{li-etal-2025-comparing,
    title = "Comparing {AI} tools and Human Raters in Predicting Reading Item Difficulty",
    author = "Li, Hongli  and
      Aldib, Roula  and
      Marchong, Chad  and
      Fan, Kevin",
    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.10/",
    pages = "84--89",
    ISBN = "979-8-218-84229-1",
    abstract = "This study compares AI tools and human raters in predicting the difficulty of reading comprehension items without response data. Predictions from AI models (ChatGPT, Gemini, Claude, and DeepSeek) and human raters are evaluated against empirical difficulty values derived from student responses. Findings will inform AI{'}s potential to support test development."
}