@inproceedings{gao-etal-2026-metrics,
    title = "Which Metrics Save the Most Human Annotation? Prediction-Powered Evaluation and Meta-Evaluation",
    author = "Gao, Mingqi  and
      Sicilia, Anthony  and
      Shi, Weiyan",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.827/",
    pages = "19215--19254",
    ISBN = "979-8-89176-459-0"
}