@article{selfdistillationformultitokenprediction, title = {Self-Distillation for Multi-Token Prediction}, author = {Guoliang Zhao and Ruobing Xie and An Wang and Shuaipeng Li and Huaibing Xie and Xingwu Sun}, year = {2026}, eprint = {2603.23911}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.23911}, }