@inproceedings{huynh-etal-2026-distribution,
title = "Distribution-aware Low-bitwidth Quantization for Large Language Models",
author = "Huynh, Bao Tan Duy and
Tsunakawa, Takashi and
Nishida, Masafumi",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.789/",
doi = "10.63317/3mnfp3i37gy2",
pages = "10057--10070",
abstract = "The increasing scale and complexity of large language models (LLMs) present significant computational and memory challenges, limiting their widespread deployment. Post-training quantization (PTQ) has emerged as a key technique for mitigating these challenges without costly retraining. However, compressing models to ultra-low bitwidths (e.g., 2-3 bits) while maintaining accuracy remains a major challenge. In this study, we present a comprehensive PTQ framework that addresses this problem by compressing LLM weights through three core innovations: (1) a calibration process guided by Kullback-Leibler divergence minimization to preserve the original weight distribution, (2) a learnable codebook optimization mechanism employing noise substitution for vector quantization to enable robust gradient estimation, and (3) a layer-grouping strategy based on statistical distribution similarity to improve parameter efficiency. Experimental evaluations on large-scale models show that the proposed framework achieves competitive performance compared with state-of-the-art quantization techniques. Importantly, these results are obtained without any post-quantization fine-tuning, highlighting the efficiency and practical applicability of our approach for deploying highly compressed LLMs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huynh-etal-2026-distribution">
<titleInfo>
<title>Distribution-aware Low-bitwidth Quantization for Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bao</namePart>
<namePart type="given">Tan</namePart>
<namePart type="given">Duy</namePart>
<namePart type="family">Huynh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Takashi</namePart>
<namePart type="family">Tsunakawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masafumi</namePart>
<namePart type="family">Nishida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The increasing scale and complexity of large language models (LLMs) present significant computational and memory challenges, limiting their widespread deployment. Post-training quantization (PTQ) has emerged as a key technique for mitigating these challenges without costly retraining. However, compressing models to ultra-low bitwidths (e.g., 2-3 bits) while maintaining accuracy remains a major challenge. In this study, we present a comprehensive PTQ framework that addresses this problem by compressing LLM weights through three core innovations: (1) a calibration process guided by Kullback-Leibler divergence minimization to preserve the original weight distribution, (2) a learnable codebook optimization mechanism employing noise substitution for vector quantization to enable robust gradient estimation, and (3) a layer-grouping strategy based on statistical distribution similarity to improve parameter efficiency. Experimental evaluations on large-scale models show that the proposed framework achieves competitive performance compared with state-of-the-art quantization techniques. Importantly, these results are obtained without any post-quantization fine-tuning, highlighting the efficiency and practical applicability of our approach for deploying highly compressed LLMs.</abstract>
<identifier type="citekey">huynh-etal-2026-distribution</identifier>
<identifier type="doi">10.63317/3mnfp3i37gy2</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.789/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>10057</start>
<end>10070</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Distribution-aware Low-bitwidth Quantization for Large Language Models
%A Huynh, Bao Tan Duy
%A Tsunakawa, Takashi
%A Nishida, Masafumi
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F huynh-etal-2026-distribution
%X The increasing scale and complexity of large language models (LLMs) present significant computational and memory challenges, limiting their widespread deployment. Post-training quantization (PTQ) has emerged as a key technique for mitigating these challenges without costly retraining. However, compressing models to ultra-low bitwidths (e.g., 2-3 bits) while maintaining accuracy remains a major challenge. In this study, we present a comprehensive PTQ framework that addresses this problem by compressing LLM weights through three core innovations: (1) a calibration process guided by Kullback-Leibler divergence minimization to preserve the original weight distribution, (2) a learnable codebook optimization mechanism employing noise substitution for vector quantization to enable robust gradient estimation, and (3) a layer-grouping strategy based on statistical distribution similarity to improve parameter efficiency. Experimental evaluations on large-scale models show that the proposed framework achieves competitive performance compared with state-of-the-art quantization techniques. Importantly, these results are obtained without any post-quantization fine-tuning, highlighting the efficiency and practical applicability of our approach for deploying highly compressed LLMs.
%R 10.63317/3mnfp3i37gy2
%U https://aclanthology.org/2026.lrec-1.789/
%U https://doi.org/10.63317/3mnfp3i37gy2
%P 10057-10070
Markdown (Informal)
[Distribution-aware Low-bitwidth Quantization for Large Language Models](https://aclanthology.org/2026.lrec-1.789/) (Huynh et al., LREC 2026)
ACL