@misc{villalobos2022will, title={Will we run out of data? Limits of LLM scaling based on human-generated data}, author={Pablo Villalobos and Anson Ho and Jaime Sevilla and Tamay Besiroglu and Lennart Heim and Marius Hobbhahn}, year={2022}, eprint={2211.04325}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2211.04325} }