@inproceedings{jung-etal-2025-model,
    title = "How Model Size, Temperature, and Prompt Style Affect {LLM}-Human Assessment Score Alignment",
    author = "Jung, Julie  and
      Lu, Max  and
      Benker, Sina Chole  and
      Darici, Dogus",
    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/author-page-yu-wang-polytechnic/2025.aimecon-main.28/",
    pages = "265--273",
    ISBN = "979-8-218-84228-4",
    abstract = "We examined how model size, temperature, and prompt style affect Large Language Models' (LLMs) alignment with human raters in assessing clinical reasoning skills. Model size emerged as a key factor in LLM-human score alignment. Findings reveal both the potential for scalable LLM-raters and the risks of relying on them exclusively."
}