@article{rephrasingnaturaltextdatawithdifferent,
  title = {Rephrasing natural text data with different languages and quality levels for Large Language Model pre-training},
  author = {Michael Pieler and Marco Bellagente and Hannah Teufel and Duy Phung and Nathan Cooper and Jonathan Tow and Paulo Rocha and Reshinth Adithyan and Zaid Alyafeai and Nikhil Pinnaparaju and Maksym Zhuravinskyi and Carlos Riquelme},
  year = {2024},
  eprint = {2410.20796},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.20796v1},
}