@inproceedings{ban-etal-2025-gap,
    title = "{GAP}: a Global Adaptive Pruning Method for Large Language Models",
    author = "Ban, Zhihua  and
      Ma, Haotian  and
      Zhang, Siheng  and
      Liu, Shengyu  and
      Chen, Xichen  and
      Yang, Ming",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1056/",
    pages = "20909--20914",
    ISBN = "979-8-89176-332-6",
    abstract = "The deployment of Large Language Models (LLMs) faces significant challenges due to high computational costs,driving the demand for effective pruning techniques. Existing structured pruning methods employ uniform compression rates across network layers, neglecting the varying importance of different network depths. To address this limitation, we propose a novel optimization framework that directly minimizes global capability loss through layer-adaptive pruning rates. The framework formulates the pruning task as a combinatorial optimization problem constrained by a total parameter budget, and an efficient dynamic programming solution is derived to determine optimal layer-wise compression rates.Experiments demonstrate that, when tuning is not included, our approach achieves comparable performance with state-of-the-art methods at high pruning rates (37-50{\%} reduction), and shows significant advantages at low pruning rates (13-25{\%} reduction). When tuning is included, our method achieves the best performance among the compared methods."
}