@article{flashbackefficientretrievalaugmented,
  title = {FlashBack:Efficient Retrieval-Augmented Language Modeling for Long Context Inference},
  author = {Runheng Liu and Xingchen Xiao and Heyan Huang and Zewen Chi and Zhijing Wu},
  year = {2024},
  eprint = {2405.04065},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2405.04065v3},
}