@article{greedyoutputapproximationtowardsefficien,
  title = {Greedy Output Approximation: Towards Efficient Structured Pruning for LLMs Without Retraining},
  author = {Jianwei Li and Yijun Dong and Qi Lei},
  year = {2024},
  eprint = {2407.19126},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.19126v1},
}