@article{matesmodelawaredataselectionfor,
  title = {MATES: Model-Aware Data Selection for Efficient Pretraining with Data Influence Models},
  author = {Zichun Yu and Spandan Das and Chenyan Xiong},
  year = {2024},
  eprint = {2406.06046},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.06046v2},
}