@article{dataefficientpretrainingwithgrouplevel,
  title = {Data-Efficient Pretraining with Group-Level Data Influence Modeling},
  author = {Zichun Yu and Fei Peng and Jie Lei and Arnold Overwijk and Wen-tau Yih and Chenyan Xiong},
  year = {2025},
  eprint = {2502.14709},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.14709v1},
}