<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2026-survey">
    <titleInfo>
        <title>A Survey on Memory-Efficient Fine-Tuning for Large Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yeachan</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mingyu</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">SangKeun</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>Fine-tuning large language models (LLMs) is a crucial process to align them with human intentions, yet this process remains memoryintensive, varying across tasks and model architectures. These huge and variable memory costs complicate scaling and deployment of LLMs, especially on limited hardware. However, existing surveys on memory efficiency are often either superficial or too narrow in scope, typically focusing on specific subfields. To address this gap, this survey presents the first systematic review of memory-efficient fine-tuning (MEFT) tailored for LLMs. To structure the research landscape, we first categorize existing approaches by their optimization environments (i.e., model itself and systems) and further classify model-based approaches by their specific optimization targets. We also discuss evaluation strategies for assessing MEFT methods and provide empirical analyses. By highlighting challenges and future directions based on current methods, this survey aims to serve as a practical guide for developing MEFT methods.</abstract>
    <identifier type="citekey">kim-etal-2026-survey</identifier>
    <identifier type="doi">10.1162/tacl.a.692</identifier>
    <location>
        <url>https://aclanthology.org/2026.tacl-1.43/</url>
    </location>
    <part>
        <date>2026</date>
        <detail type="volume"><number>14</number></detail>
        <extent unit="page">
            <start>960</start>
            <end>982</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T A Survey on Memory-Efficient Fine-Tuning for Large Language Models
%A Kim, Yeachan
%A Lee, Mingyu
%A Lee, SangKeun
%J Transactions of the Association for Computational Linguistics
%D 2026
%V 14
%I MIT Press
%C Cambridge, MA
%F kim-etal-2026-survey
%X Fine-tuning large language models (LLMs) is a crucial process to align them with human intentions, yet this process remains memoryintensive, varying across tasks and model architectures. These huge and variable memory costs complicate scaling and deployment of LLMs, especially on limited hardware. However, existing surveys on memory efficiency are often either superficial or too narrow in scope, typically focusing on specific subfields. To address this gap, this survey presents the first systematic review of memory-efficient fine-tuning (MEFT) tailored for LLMs. To structure the research landscape, we first categorize existing approaches by their optimization environments (i.e., model itself and systems) and further classify model-based approaches by their specific optimization targets. We also discuss evaluation strategies for assessing MEFT methods and provide empirical analyses. By highlighting challenges and future directions based on current methods, this survey aims to serve as a practical guide for developing MEFT methods.
%R 10.1162/tacl.a.692
%U https://aclanthology.org/2026.tacl-1.43/
%U https://doi.org/10.1162/tacl.a.692
%P 960-982

Markdown (Informal)

[A Survey on Memory-Efficient Fine-Tuning for Large Language Models](https://aclanthology.org/2026.tacl-1.43/) (Kim et al., TACL 2026)

• A Survey on Memory-Efficient Fine-Tuning for Large Language Models (Kim et al., TACL 2026)

ACL

• Yeachan Kim, Mingyu Lee, and SangKeun Lee. 2026. A Survey on Memory-Efficient Fine-Tuning for Large Language Models. Transactions of the Association for Computational Linguistics, 14:960–982.