@article{promptinternsavinginferencecostsby,
  title = {PromptIntern: Saving Inference Costs by Internalizing Recurrent Prompt during Large Language Model Fine-tuning},
  author = {Jiaru Zou and Mengyu Zhou and Tao Li and Shi Han and Dongmei Zhang},
  year = {2024},
  eprint = {2407.02211},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.02211v2},
}