@inproceedings{diddee-etal-2026-benchbrowser,
    title = "{B}ench{B}rowser: Retrieving Evidence for Evaluating Benchmark Validity",
    author = "Diddee, Harshita  and
      Yauney, Gregory  and
      Swayamdipta, Swabha  and
      Ippolito, Daphne",
    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.1755/",
    pages = "40024--40053",
    ISBN = "979-8-89176-459-0"
}