@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://aclanthology.org/2026.acl-long.2213/",
doi = "10.18653/v1/2026.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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yun-etal-2026-sharvet">
<titleInfo>
<title>SharVeT: Similarity-aware Parameter Sharing with Vector-based Tuning for Efficient LLM Compression</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jeongin</namePart>
<namePart type="family">Yun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaeri</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jongjin</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minjun</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinho</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">U</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<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.</abstract>
<identifier type="citekey">yun-etal-2026-sharvet</identifier>
<identifier type="doi">10.18653/v1/2026.acl-long.2213</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.2213/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>47921</start>
<end>47937</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SharVeT: Similarity-aware Parameter Sharing with Vector-based Tuning for Efficient LLM Compression
%A Yun, Jeongin
%A Lee, Jaeri
%A Kim, Jongjin
%A Kim, Minjun
%A Song, Jinho
%A Kang, U.
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F yun-etal-2026-sharvet
%X 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.
%R 10.18653/v1/2026.acl-long.2213
%U https://aclanthology.org/2026.acl-long.2213/
%U https://doi.org/10.18653/v1/2026.acl-long.2213
%P 47921-47937
Markdown (Informal)
[SharVeT: Similarity-aware Parameter Sharing with Vector-based Tuning for Efficient LLM Compression](https://aclanthology.org/2026.acl-long.2213/) (Yun et al., ACL 2026)
ACL