@inproceedings{huang-etal-2024-context,
    title = "Context-Aware Assistant Selection for Improved Inference Acceleration with Large Language Models",
    author = "Huang, Jerry  and
      Parthasarathi, Prasanna  and
      Rezagholizadeh, Mehdi  and
      Chandar, Sarath",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.emnlp-main.332/",
    doi = "10.18653/v1/2024.emnlp-main.332",
    pages = "5817--5830"
}