<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2024-ra">
    <titleInfo>
        <title>RA-LoRA: Rank-Adaptive Parameter-Efficient Fine-Tuning for Accurate 2-bit Quantized Large Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Minsoo</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sihwa</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wonyong</namePart>
        <namePart type="family">Sung</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jungwook</namePart>
        <namePart type="family">Choi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics ACL 2024</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Lun-Wei</namePart>
            <namePart type="family">Ku</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Andre</namePart>
            <namePart type="family">Martins</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Vivek</namePart>
            <namePart type="family">Srikumar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Bangkok, Thailand and virtual meeting</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Deploying large language models (LLMs) with their extensive parameters and high memory demands challenges computational efficiency, particularly in fine-tuning for specific applications with limited resources. Techniques like Low-Rank Adaptation (LoRA) help by training a smaller, modifiable extension of the base model to reduce memory usage. However, combining quantization with LoRA, especially in low-bit scenarios, can lead to performance losses due to quantization errors. Our innovative Rank-Adaptive LoRA (RA-LoRA) addresses this by dynamically adjusting the adapter’s rank using rank-subspace analysis, optimizing performance with fewer parameters. We tested RA-LoRA on state-of-the-art LLMs for 2-bit efficient fine-tuning, showing it can improve model accuracy with minimal trainable parameters, marking a leap forward in quantization-aware fine-tuning methods and highlighting the significance of rank dynamics in optimizing quantized LLMs.</abstract>
    <identifier type="citekey">kim-etal-2024-ra</identifier>
    <location>
        <url>https://aclanthology.org/2024.findings-acl.933</url>
    </location>
    <part>
        <date>2024-08</date>
        <extent unit="page">
            <start>15773</start>
            <end>15786</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T RA-LoRA: Rank-Adaptive Parameter-Efficient Fine-Tuning for Accurate 2-bit Quantized Large Language Models
%A Kim, Minsoo
%A Lee, Sihwa
%A Sung, Wonyong
%A Choi, Jungwook
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F kim-etal-2024-ra
%X Deploying large language models (LLMs) with their extensive parameters and high memory demands challenges computational efficiency, particularly in fine-tuning for specific applications with limited resources. Techniques like Low-Rank Adaptation (LoRA) help by training a smaller, modifiable extension of the base model to reduce memory usage. However, combining quantization with LoRA, especially in low-bit scenarios, can lead to performance losses due to quantization errors. Our innovative Rank-Adaptive LoRA (RA-LoRA) addresses this by dynamically adjusting the adapter’s rank using rank-subspace analysis, optimizing performance with fewer parameters. We tested RA-LoRA on state-of-the-art LLMs for 2-bit efficient fine-tuning, showing it can improve model accuracy with minimal trainable parameters, marking a leap forward in quantization-aware fine-tuning methods and highlighting the significance of rank dynamics in optimizing quantized LLMs.
%U https://aclanthology.org/2024.findings-acl.933
%P 15773-15786

Markdown (Informal)

[RA-LoRA: Rank-Adaptive Parameter-Efficient Fine-Tuning for Accurate 2-bit Quantized Large Language Models](https://aclanthology.org/2024.findings-acl.933) (Kim et al., Findings 2024)

• RA-LoRA: Rank-Adaptive Parameter-Efficient Fine-Tuning for Accurate 2-bit Quantized Large Language Models (Kim et al., Findings 2024)

ACL

• Minsoo Kim, Sihwa Lee, Wonyong Sung, and Jungwook Choi. 2024. RA-LoRA: Rank-Adaptive Parameter-Efficient Fine-Tuning for Accurate 2-bit Quantized Large Language Models. In Findings of the Association for Computational Linguistics ACL 2024, pages 15773–15786, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.