Chang Liu 0076, Chongyang Tao, Jianxin Liang, Jiazhan Feng, Tao Shen 0001, Quzhe Huang, Dongyan Zhao 0001. Length-Adaptive Distillation: Customizing Small Language Model for Dynamic Token Pruning. In Houda Bouamor, Juan Pino 0001, Kalika Bali, editors, Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, December 6-10, 2023. pages 4452-4463, Association for Computational Linguistics, 2023. [doi]
Abstract is missing.