@inproceedings{maximov-etal-2026-2,
    title = "From 2:4 to 8:16 sparsity patterns in {LLM}s for Outliers and Weights with Variance Correction",
    author = "Maximov, Egor  and
      Kuzkina, Yulia  and
      Shvetsov, Egor  and
      Kanametov, Azamat  and
      Prutko, Aleksandr  and
      Zhelnin, Maxim  and
      Goncharov, Aleksei",
    editor = "Li, Yunyao  and
      Rehm, Georg  and
      Tu, Mei",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-industry.66/",
    pages = "957--965",
    ISBN = "979-8-89176-394-4",
    abstract = "As large language models (LLMs) grow in size, efficient compression techniques like quantization and sparsification are critical. While quantization maintains performance with reduced precision, structured sparsity methods, such as N:M sparsification, often fall short due to limited flexibility and sensitivity to outlier weights. We explore 8:16 semi-structured sparsity, demonstrating its ability to surpass the Performance Threshold{---}where a compressed model matches the accuracy of its uncompressed or smaller counterpart under equivalent memory constraints. Compared to 2:4 sparsity, 8:16 offers greater flexibility with minimal storage overhead (0.875 vs. 0.75 bits/element). We also apply sparse structured patterns for salient weights, showing that structured sparsity for outliers is competitive with unstructured approaches, leading to equivalent or better results. Finally, we demonstrate that simple techniques such as variance correction and SmoothQuant-like weight equalization improve sparse models performance."
}