@article{raeeatrainingfreeretrievalaugmented, title = {RAEE: A Robust Retrieval-Augmented Early Exiting Framework for Efficient Inference}, author = {Lianming Huang and Shangyu Wu and Yufei Cui and Ying Xiong and Xue Liu and Tei-Wei Kuo and Nan Guan and Chun Jason Xue}, year = {2024}, eprint = {2405.15198}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2405.15198v2}, }