@article{lbpelongtokenfirsttokenizationtoimprove, title = {LBPE: Long-token-first Tokenization to Improve Large Language Models}, author = {Haoran Lian and Yizhe Xiong and Zijia Lin and Jianwei Niu and Shasha Mo and Hui Chen and Peng Liu and Guiguang Ding}, year = {2024}, eprint = {2411.05504}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2411.05504v1}, }