@inproceedings{zou-etal-2024-promptintern,
    title = "{P}rompt{I}ntern: Saving Inference Costs by Internalizing Recurrent Prompt during Large Language Model Fine-tuning",
    author = "Zou, Jiaru  and
      Zhou, Mengyu  and
      Li, Tao  and
      Han, Shi  and
      Zhang, Dongmei",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.findings-emnlp.602/",
    doi = "10.18653/v1/2024.findings-emnlp.602",
    pages = "10288--10305"
}