@article{nearestneighborspeculativedecodingforllm, title = {Nearest Neighbor Speculative Decoding for LLM Generation and Attribution}, author = {Minghan Li and Xilun Chen and Ari Holtzman and Beidi Chen and Jimmy Lin and Wen-tau Yih and Xi Victoria Lin}, year = {2024}, eprint = {2405.19325}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2405.19325v2}, }