@inproceedings{ji-sun-2026-ocp,
    title = "{OCP}: Outlier-Centric Probing for Dynamic Structured Pruning of {LLM}s",
    author = "Ji, Yang  and
      Sun, Ying",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.276/",
    pages = "6108--6124",
    ISBN = "979-8-89176-390-6",
    abstract = "Structured pruning offers a hardware-friendly approach for efficient LLM inference. Early static methods determine fixed subnetworks through offline calibration, suffering from performance degradation and calibration sensitivity. Recent methods explore input-adaptive pruning by selecting a subset of tokens as probes to estimate hidden activations for online pruning decisions.However, existing probe selection strategies fail to identify outlier-triggering tokens, and uniform layer-wise sparsity misaligns with heterogeneous outlier distributions, leading to critical channels being incorrectly pruned. Therefore, we propose OCP (Outlier-Centric Probing for structured pruning), a principled framework that prioritizes capturing outlier-triggering tokens rather than reconstructing full hidden distributions. Specifically, OCP includes three key components: (1) sensitivity-weighted probing for FFN layers that identifies outlier patterns via precomputed weight aggregations, (2) attention-accumulated probing that leverages preceding attention matrices to identify salient tokens, and (3) online adaptive sparsity allocation that dynamically adjusts layer-wise pruning based on history-guided outlier statistics. Extensive experiments on LLaMA2, LLaMA3, and OPT demonstrate that OCP consistently outperforms state-of-the-art methods across benchmarks, achieving up to 25{\%} perplexity reduction at 1.6$\times$ speedup."
}