@inproceedings{dataselectionforlanguagemodelsvia1,
  title = {Data Selection for Language Models via Importance Resampling},
  author = {Sang Michael Xie and Shibani Santurkar and Tengyu Ma and Percy Liang},
  year = {2023},
  booktitle = {NeurIPS 2023 11},
  eprint = {2302.03169},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2302.03169v3},
}