@inproceedings{he-etal-2024-rest,
    title = "{REST}: Retrieval-Based Speculative Decoding",
    author = "He, Zhenyu  and
      Zhong, Zexuan  and
      Cai, Tianle  and
      Lee, Jason  and
      He, Di",
    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.88/",
    doi = "10.18653/v1/2024.naacl-long.88",
    pages = "1582--1595"
}