@misc{tirumala2023improving, title={D4: Improving LLM Pretraining via Document De-Duplication and Diversification}, author={Kushal Tirumala and Daniel Simig and Armen Aghajanyan and Ari S. Morcos}, year={2023}, eprint={2308.12284}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2308.12284} }