@article{farewelltoaimlesslargescalepretraining,
  title = {Farewell to Aimless Large-scale Pretraining: Influential Subset Selection for Language Model},
  author = {Xiao Wang and Weikang Zhou and Qi Zhang and Jie zhou and Songyang Gao and Junzhe Wang and Menghan Zhang and Xiang Gao and Yunwen Chen and Tao Gui},
  year = {2023},
  eprint = {2305.12816},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2305.12816v1},
}