<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shamrai-2024-language">
    <titleInfo>
        <title>Language-Specific Pruning for Efficient Reduction of Large Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Maksym</namePart>
        <namePart type="family">Shamrai</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Third Ukrainian Natural Language Processing Workshop (UNLP) @ LREC-COLING 2024</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Mariana</namePart>
            <namePart type="family">Romanyshyn</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nataliia</namePart>
            <namePart type="family">Romanyshyn</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Andrii</namePart>
            <namePart type="family">Hlybovets</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Oleksii</namePart>
            <namePart type="family">Ignatenko</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>ELRA and ICCL</publisher>
            <place>
                <placeTerm type="text">Torino, Italia</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Delving into pruning techniques is essential to boost the efficiency of Large Language Models (LLMs) by reducing their size and computational demands, resulting in faster and more cost-effective inference. In this work, our key contribution lies in recognizing that LLMs trained on diverse languages manifest distinct language-specific weight distributions. Exploiting this insight, we illustrate that pruning LLMs using language-specific data results in a more potent model compression. Empirical evidence underscores the critical nature of pruning on language-specific data, highlighting a noteworthy impact on the perplexity of Ukrainian texts compared to pruning on English data. The proposed methodology significantly reduces the size of LLaMA, LLaMA 2 and Mistral models while preserving competitive performance. This research underscores the significance of linguistic considerations in LLM pruning and advocates for language-specific optimization, establishing a framework for more efficient and tailored language models across diverse linguistic contexts. Additionally, all experiments were conducted using a single consumer-grade NVIDIA RTX 3090 GPU, and the code is available at https://github.com/mshamrai/language-specific-pruning.</abstract>
    <identifier type="citekey">shamrai-2024-language</identifier>
    <location>
        <url>https://aclanthology.org/2024.unlp-1.16</url>
    </location>
    <part>
        <date>2024-05</date>
        <extent unit="page">
            <start>135</start>
            <end>140</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Language-Specific Pruning for Efficient Reduction of Large Language Models
%A Shamrai, Maksym
%Y Romanyshyn, Mariana
%Y Romanyshyn, Nataliia
%Y Hlybovets, Andrii
%Y Ignatenko, Oleksii
%S Proceedings of the Third Ukrainian Natural Language Processing Workshop (UNLP) @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F shamrai-2024-language
%X Delving into pruning techniques is essential to boost the efficiency of Large Language Models (LLMs) by reducing their size and computational demands, resulting in faster and more cost-effective inference. In this work, our key contribution lies in recognizing that LLMs trained on diverse languages manifest distinct language-specific weight distributions. Exploiting this insight, we illustrate that pruning LLMs using language-specific data results in a more potent model compression. Empirical evidence underscores the critical nature of pruning on language-specific data, highlighting a noteworthy impact on the perplexity of Ukrainian texts compared to pruning on English data. The proposed methodology significantly reduces the size of LLaMA, LLaMA 2 and Mistral models while preserving competitive performance. This research underscores the significance of linguistic considerations in LLM pruning and advocates for language-specific optimization, establishing a framework for more efficient and tailored language models across diverse linguistic contexts. Additionally, all experiments were conducted using a single consumer-grade NVIDIA RTX 3090 GPU, and the code is available at https://github.com/mshamrai/language-specific-pruning.
%U https://aclanthology.org/2024.unlp-1.16
%P 135-140

Markdown (Informal)

[Language-Specific Pruning for Efficient Reduction of Large Language Models](https://aclanthology.org/2024.unlp-1.16) (Shamrai, UNLP 2024)

• Language-Specific Pruning for Efficient Reduction of Large Language Models (Shamrai, UNLP 2024)

ACL

• Maksym Shamrai. 2024. Language-Specific Pruning for Efficient Reduction of Large Language Models. In Proceedings of the Third Ukrainian Natural Language Processing Workshop (UNLP) @ LREC-COLING 2024, pages 135–140, Torino, Italia. ELRA and ICCL.