@article{rethinkingkullbackleiblerdivergencein, title = {Rethinking Kullback-Leibler Divergence in Knowledge Distillation for Large Language Models}, author = {Taiqiang Wu and Chaofan Tao and Jiahao Wang and Runming Yang and Zhe Zhao and Ngai Wong}, year = {2024}, eprint = {2404.02657}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2404.02657v4}, }