@article{scalinglawsofsyntheticdataforlanguage, title = {Scaling Laws of Synthetic Data for Language Models}, author = {Zeyu Qin and Qingxiu Dong and Xingxing Zhang and Li Dong and Xiaolong Huang and ZiYi Yang and Mahmoud Khademi and Dongdong Zhang and Hany Hassan Awadalla and Yi R. Fung and Weizhu Chen and Minhao Cheng and Furu Wei}, year = {2025}, eprint = {2503.19551}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.19551v2}, }