@article{tokencleaningfinegraineddataselection, title = {Token Cleaning: Fine-Grained Data Selection for LLM Supervised Fine-Tuning}, author = {Jinlong Pang and Na Di and Zhaowei Zhu and Jiaheng Wei and Hao Cheng and Chen Qian and Yang Liu}, year = {2025}, eprint = {2502.01968}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2502.01968v1}, }