@misc{liu2024datasets, title={Datasets for Large Language Models: A Comprehensive Survey}, author={Yang Liu and Jiahuan Cao and Chongyu Liu and Kai Ding and Lianwen Jin}, year={2024}, eprint={2402.18041}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2402.18041} }