@article{dataconstrainedlanguagemodelpretrainingi, title = {Data-Constrained Language Model Pretraining: Improved Regularization and Scaling Laws}, author = {Zhiwei Xu and Shihao Wu and Hanseul Cho and Wei Hu and Yixin Wang}, year = {2026}, eprint = {2606.06888}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.06888}, }