@inproceedings{chen-etal-2025-faster,
    title = "Faster In-Context Learning for {LLM}s via N-Gram Trie Speculative Decoding",
    author = "Chen, Jinglin  and
      Li, Qiwei  and
      Li, Zuchao  and
      Qi, Baoyuan  and
      Guoming, Liu  and
      Ai, Haojun  and
      Zhao, Hai  and
      Wang, Ping",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.911/",
    pages = "18051--18062",
    ISBN = "979-8-89176-332-6"
}