@article{datamanagementforlargelanguagemodelsa, title = {Data Management For Training Large Language Models: A Survey}, author = {Zige Wang and Wanjun Zhong and YuFei Wang and Qi Zhu and Fei Mi and Baojun Wang and Lifeng Shang and Xin Jiang and Qun Liu}, year = {2023}, eprint = {2312.01700}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2312.01700v3}, }