@inproceedings{yi-etal-2024-generation,
    title = "Generation Meets Verification: Accelerating Large Language Model Inference with Smart Parallel Auto-Correct Decoding",
    author = "Yi, Hanling  and
      Lin, Feng  and
      Li, Hongbin  and
      Peiyang, Ning  and
      Yu, Xiaotian  and
      Xiao, Rong",
    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/jlcl-multiple-ingestion/2024.findings-acl.313/",
    doi = "10.18653/v1/2024.findings-acl.313",
    pages = "5285--5299"
}