@article{demystifyingdataorganizationforenhancedl, title = {Demystifying Data Organization for Enhanced LLM Training}, author = {Yalun Dai and Yangyu Huang and Tongshen Yang and Yonghan Wang and Xin Zhang and Wenshan Wu and Qihao Zhao and Hao Li and Yuanyuan Gao and Kim-Hui Yap and Scarlett Li}, year = {2026}, eprint = {2605.30334}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.30334}, }