@inproceedings{liu-etal-2024-speculative-decoding,
    title = "Speculative Decoding via Early-exiting for Faster {LLM} Inference with {T}hompson Sampling Control Mechanism",
    author = "Liu, Jiahao  and
      Wang, Qifan  and
      Wang, Jingang  and
      Cai, Xunliang",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Add-Cong-Liu-Florida-Atlantic-University-author-id/2024.findings-acl.179/",
    doi = "10.18653/v1/2024.findings-acl.179",
    pages = "3027--3043"
}