%0 Journal Article %1 journals/corr/abs-2308-12284 %A Tirumala, Kushal %A Simig, Daniel %A Aghajanyan, Armen %A Morcos, Ari S. %D 2023 %J CoRR %K dblp %T D4: Improving LLM Pretraining via Document De-Duplication and Diversification. %U http://dblp.uni-trier.de/db/journals/corr/corr2308.html#abs-2308-12284 %V abs/2308.12284

@article{journals/corr/abs-2308-12284, added-at = {2023-08-30T00:00:00.000+0200}, author = {Tirumala, Kushal and Simig, Daniel and Aghajanyan, Armen and Morcos, Ari S.}, biburl = {https://www.bibsonomy.org/bibtex/2c57d59549d71963ab6069572e9611846/dblp}, ee = {https://doi.org/10.48550/arXiv.2308.12284}, interhash = {b6f86de47047148789fdf61f62b27726}, intrahash = {c57d59549d71963ab6069572e9611846}, journal = {CoRR}, keywords = {dblp}, timestamp = {2024-04-09T00:22:29.000+0200}, title = {D4: Improving LLM Pretraining via Document De-Duplication and Diversification.}, url = {http://dblp.uni-trier.de/db/journals/corr/corr2308.html#abs-2308-12284}, volume = {abs/2308.12284}, year = 2023 }