@inproceedings{liu-etal-2023-tcra,
    title = "{TCRA}-{LLM}: Token Compression Retrieval Augmented Large Language Model for Inference Cost Reduction",
    author = "Liu, Junyi  and
      Li, Liangzhi  and
      Xiang, Tong  and
      Wang, Bowen  and
      Qian, Yiming",
    editor = "Bouamor, Houda  and
      Pino, Juan  and
      Bali, Kalika",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/moar-dois/2023.findings-emnlp.655/",
    doi = "10.18653/v1/2023.findings-emnlp.655",
    pages = "9796--9810"
}