@inproceedings{wadi-fredette-2025-monte,
    title = "A {M}onte-{C}arlo Sampling Framework For Reliable Evaluation of Large Language Models Using Behavioral Analysis",
    author = "Wadi, Davood  and
      Fredette, Marc",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.500/",
    doi = "10.18653/v1/2025.findings-emnlp.500",
    pages = "9414--9432",
    ISBN = "979-8-89176-335-7"
}