@article{acceleratinginferenceofretrievalaugmente, title = {Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selection}, author = {Yun Zhu and Jia-Chen Gu and Caitlin Sikora and Ho Ko and Yinxiao Liu and Chu-Cheng Lin and Lei Shu and Liangchen Luo and Lei Meng and Bang Liu and Jindong Chen}, year = {2024}, eprint = {2405.16178}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2405.16178v1}, }