@inproceedings{yun-etal-2026-sharvet,
    title = "{S}har{V}e{T}: Similarity-aware Parameter Sharing with Vector-based Tuning for Efficient {LLM} Compression",
    author = "Yun, Jeongin  and
      Lee, Jaeri  and
      Kim, Jongjin  and
      Kim, Minjun  and
      Song, Jinho  and
      Kang, U",
    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.2213/",
    pages = "47921--47937",
    ISBN = "979-8-89176-390-6",
    abstract = "How can we share parameters within large language models to significantly reduce memory costs while preserving accuracy? While parameter sharing is a promising solution to the memory overhead of large language models, existing methods rely on naive grouping and fail to correct sharing-induced discrepancies. We propose an accurate and efficient parameter sharing framework, SharVeT (Similarity-aware sharing with Vector-based Tuning), which performs similarity-based grouping to ensure accurate sharing, allocates parameters adaptively to preserve diversity within each group, and applies lightweight refinement with knowledge distillation to correct sharing-induced discrepancies. Experiments show that SharVeT outperforms existing sharing methods, achieving up to 32.1{\%} lower perplexity and 23.3{\%} higher few-shot reasoning accuracy."
}