<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rios-etal-2025-sparsity">
    <titleInfo>
        <title>Sparsity May Be All You Need: Sparse Random Parameter Adaptation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jesus</namePart>
        <namePart type="family">Rios</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pierre</namePart>
        <namePart type="family">Dognin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ronny</namePart>
        <namePart type="family">Luss</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Karthikeyan</namePart>
        <namePart type="family">Natesan Ramamurthy</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Christos</namePart>
            <namePart type="family">Christodoulopoulos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tanmoy</namePart>
            <namePart type="family">Chakraborty</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Carolyn</namePart>
            <namePart type="family">Rose</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Violet</namePart>
            <namePart type="family">Peng</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Suzhou, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-335-7</identifier>
    </relatedItem>
    <abstract>Full fine-tuning of large language models for alignment and task adaptation has become prohibitively expensive as models have grown in size. Parameter-Efficient Fine-Tuning (PEFT) methods aim at significantly reducing the computational and memory resources needed for fine-tuning these models by only training on a small number of parameters instead of all model parameters. Currently, the most popular PEFT method is the Low-Rank Adaptation (LoRA), which freezes the parameters of the model and introduces a small set of trainable parameters in the form of low-rank matrices. We propose simply reducing the number of trainable parameters by randomly selecting a small proportion of the model parameters to train on, while fixing all other parameters, without any additional prior assumptions such as low-rank structures. In this paper, we compare the efficiency and performance of our proposed approach to other PEFT methods as well as full parameter fine-tuning. We find our method to be competitive with LoRA when using a similar number of trainable parameters. Our findings suggest that what truly matters for a PEFT technique to perform well is not necessarily the specific adapter structure, but rather the number of trainable parameters being used.</abstract>
    <identifier type="citekey">rios-etal-2025-sparsity</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-emnlp.1013/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>18650</start>
            <end>18666</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Sparsity May Be All You Need: Sparse Random Parameter Adaptation
%A Rios, Jesus
%A Dognin, Pierre
%A Luss, Ronny
%A Natesan Ramamurthy, Karthikeyan
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F rios-etal-2025-sparsity
%X Full fine-tuning of large language models for alignment and task adaptation has become prohibitively expensive as models have grown in size. Parameter-Efficient Fine-Tuning (PEFT) methods aim at significantly reducing the computational and memory resources needed for fine-tuning these models by only training on a small number of parameters instead of all model parameters. Currently, the most popular PEFT method is the Low-Rank Adaptation (LoRA), which freezes the parameters of the model and introduces a small set of trainable parameters in the form of low-rank matrices. We propose simply reducing the number of trainable parameters by randomly selecting a small proportion of the model parameters to train on, while fixing all other parameters, without any additional prior assumptions such as low-rank structures. In this paper, we compare the efficiency and performance of our proposed approach to other PEFT methods as well as full parameter fine-tuning. We find our method to be competitive with LoRA when using a similar number of trainable parameters. Our findings suggest that what truly matters for a PEFT technique to perform well is not necessarily the specific adapter structure, but rather the number of trainable parameters being used.
%U https://aclanthology.org/2025.findings-emnlp.1013/
%P 18650-18666

Markdown (Informal)

[Sparsity May Be All You Need: Sparse Random Parameter Adaptation](https://aclanthology.org/2025.findings-emnlp.1013/) (Rios et al., Findings 2025)

• Sparsity May Be All You Need: Sparse Random Parameter Adaptation (Rios et al., Findings 2025)

ACL

• Jesus Rios, Pierre Dognin, Ronny Luss, and Karthikeyan Natesan Ramamurthy. 2025. Sparsity May Be All You Need: Sparse Random Parameter Adaptation. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 18650–18666, Suzhou, China. Association for Computational Linguistics.