@inproceedings{sottana-etal-2023-evaluation,
    title = "Evaluation Metrics in the Era of {GPT}-4: Reliably Evaluating Large Language Models on Sequence to Sequence Tasks",
    author = "Sottana, Andrea  and
      Liang, Bin  and
      Zou, Kai  and
      Yuan, Zheng",
    editor = "Bouamor, Houda  and
      Pino, Juan  and
      Bali, Kalika",
    booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2023.emnlp-main.543/",
    doi = "10.18653/v1/2023.emnlp-main.543",
    pages = "8776--8788"
}