@article{improvingknowledgedistillationforbert, title = {Improving Knowledge Distillation for BERT Models: Loss Functions, Mapping Methods, and Weight Tuning}, author = {Apoorv Dankar and Adeem Jassani and Kartikaeya Kumar}, year = {2023}, eprint = {2308.13958}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2308.13958v1}, }