@inproceedings{zhang-etal-2025-memotune,
title = "{M}e{M}o{T}une: A Measure and Moment-Driven Fine-Tuning Framework for Quantized Large Language Models",
author = "Zhang, Yun and
Geng, Xue and
Liao, Lizi and
Sun, Jintong and
Yu, Minghe and
Yu, Ge",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.208/",
doi = "10.18653/v1/2025.findings-acl.208",
pages = "4036--4050",
ISBN = "979-8-89176-256-5",
abstract = "Quantizing large language models (LLMs) is essential for reducing memory and computational costs in natural language processing. Existing methods combine quantization with parameter-efficient fine-tuning but often fail to meet practical performance requirements. This paper introduces MeMoTune, a novel fine-tuning framework for quantized LLMs. By employing a measure and moment approach within a low-rank approximation framework in probability measure space, MeMoTune optimizes the objective function for superior fine-tuning results. The update process is further refined through scaled gradient, enhancing convergence efficiency and noise robustness. Experiments on tasks like text generation, summarization, and understanding show MeMoTune significantly outperforms state-of-the-art methods, e.g. fine-tuning Llama2-13B on GSM8K improves accuracy by 5.5{\%}, while fine-tuning DeBERTaV3-base on CoLA of GLUE increases Matthews correlation by 1.7{\%}. The code is publicly available at: https://github.com/hddyyyb/MeMoTune."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2025-memotune">
<titleInfo>
<title>MeMoTune: A Measure and Moment-Driven Fine-Tuning Framework for Quantized Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xue</namePart>
<namePart type="family">Geng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lizi</namePart>
<namePart type="family">Liao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jintong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghe</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ge</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>Quantizing large language models (LLMs) is essential for reducing memory and computational costs in natural language processing. Existing methods combine quantization with parameter-efficient fine-tuning but often fail to meet practical performance requirements. This paper introduces MeMoTune, a novel fine-tuning framework for quantized LLMs. By employing a measure and moment approach within a low-rank approximation framework in probability measure space, MeMoTune optimizes the objective function for superior fine-tuning results. The update process is further refined through scaled gradient, enhancing convergence efficiency and noise robustness. Experiments on tasks like text generation, summarization, and understanding show MeMoTune significantly outperforms state-of-the-art methods, e.g. fine-tuning Llama2-13B on GSM8K improves accuracy by 5.5%, while fine-tuning DeBERTaV3-base on CoLA of GLUE increases Matthews correlation by 1.7%. The code is publicly available at: https://github.com/hddyyyb/MeMoTune.</abstract>
<identifier type="citekey">zhang-etal-2025-memotune</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.208</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.208/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>4036</start>
<end>4050</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MeMoTune: A Measure and Moment-Driven Fine-Tuning Framework for Quantized Large Language Models
%A Zhang, Yun
%A Geng, Xue
%A Liao, Lizi
%A Sun, Jintong
%A Yu, Minghe
%A Yu, Ge
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F zhang-etal-2025-memotune
%X Quantizing large language models (LLMs) is essential for reducing memory and computational costs in natural language processing. Existing methods combine quantization with parameter-efficient fine-tuning but often fail to meet practical performance requirements. This paper introduces MeMoTune, a novel fine-tuning framework for quantized LLMs. By employing a measure and moment approach within a low-rank approximation framework in probability measure space, MeMoTune optimizes the objective function for superior fine-tuning results. The update process is further refined through scaled gradient, enhancing convergence efficiency and noise robustness. Experiments on tasks like text generation, summarization, and understanding show MeMoTune significantly outperforms state-of-the-art methods, e.g. fine-tuning Llama2-13B on GSM8K improves accuracy by 5.5%, while fine-tuning DeBERTaV3-base on CoLA of GLUE increases Matthews correlation by 1.7%. The code is publicly available at: https://github.com/hddyyyb/MeMoTune.
%R 10.18653/v1/2025.findings-acl.208
%U https://aclanthology.org/2025.findings-acl.208/
%U https://doi.org/10.18653/v1/2025.findings-acl.208
%P 4036-4050
Markdown (Informal)
[MeMoTune: A Measure and Moment-Driven Fine-Tuning Framework for Quantized Large Language Models](https://aclanthology.org/2025.findings-acl.208/) (Zhang et al., Findings 2025)
ACL