@inproceedings{lin-etal-2024-slim, title = "{SL}i{M}: Speculative Decoding with Hypothesis Reduction", author = "Lin, Chi-Heng and Tuli, Shikhar and Smith, James and Hsu, Yen-Chang and Shen, Yilin and Jin, Hongxia", editor = "Duh, Kevin and Gomez, Helena and Bethard, Steven", booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024", month = jun, year = "2024", address = "Mexico City, Mexico", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2024.findings-naacl.63/", doi = "10.18653/v1/2024.findings-naacl.63", pages = "1005--1017" }