@article{llmlinguacompressingpromptsforaccelerate,
  title = {LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models},
  author = {Huiqiang Jiang and Qianhui Wu and Chin-Yew Lin and Yuqing Yang and Lili Qiu},
  year = {2023},
  eprint = {2310.05736},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2310.05736v2},
}