@misc{xu2023compress,
  title={Compress, Then Prompt: Improving Accuracy-Efficiency Trade-off of LLM Inference with Transferable Prompt},
  author={Zhaozhuo Xu and Zirui Liu and Beidi Chen and Yuxin Tang and Jue Wang and Kaixiong Zhou and Xia Hu and Anshumali Shrivastava},
  year={2023},
  eprint={2305.11186},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2305.11186}
}