@inproceedings{hardy-2025-glitters,
    title = "{\textquotedblleft}All that Glitters{\textquotedblright}: Techniques for Evaluations with Unreliable Model and Human Annotations",
    author = "Hardy, Michael",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.findings-naacl.120/",
    pages = "2250--2278",
    ISBN = "979-8-89176-195-7"
}