@misc{liu2024best, title={Best Practices and Lessons Learned on Synthetic Data for Language Models}, author={Ruibo Liu and Jerry Wei and Fangyu Liu and Chenglei Si and Yanzhe Zhang and Jinmeng Rao and Steven Zheng and Daiyi Peng and Diyi Yang and Denny Zhou and Andrew M. Dai}, year={2024}, eprint={2404.07503}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2404.07503} }