@inproceedings{longpre-etal-2024-pretrainers,
    title = "A Pretrainer`s Guide to Training Data: Measuring the Effects of Data Age, Domain Coverage, Quality, {\&} Toxicity",
    author = "Longpre, Shayne  and
      Yauney, Gregory  and
      Reif, Emily  and
      Lee, Katherine  and
      Roberts, Adam  and
      Zoph, Barret  and
      Zhou, Denny  and
      Wei, Jason  and
      Robinson, Kevin  and
      Mimno, David  and
      Ippolito, Daphne",
    editor = "Duh, Kevin  and
      Gomez, Helena  and
      Bethard, Steven",
    booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.naacl-long.179/",
    doi = "10.18653/v1/2024.naacl-long.179",
    pages = "3245--3276"
}