<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xiao-etal-2024-lm">
    <titleInfo>
        <title>LM-Cocktail: Resilient Tuning of Language Models via Model Merging</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Shitao</namePart>
        <namePart type="family">Xiao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zheng</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Peitian</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xingrun</namePart>
        <namePart type="family">Xing</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>The pre-trained language models are continually fine-tuned to better support downstream applications. However, this operation may result in significant performance degeneration on general tasks beyond the targeted domain. To overcome this problem, we propose LM-Cocktail which enables the fine-tuned model to stay resilient in general perspectives. Our method is conducted in the form of model merging, where the fine-tuned language model is merged with the pre-trained base model or the peer models from other domains through weighted average. Despite simplicity, LM-Cocktail is surprisingly effective: the resulted model is able to achieve a strong empirical performance in the whole scope of general tasks while preserving a superior capacity in its targeted domain.</abstract>
    <identifier type="citekey">xiao-etal-2024-lm</identifier>
    <location>
        <url>https://aclanthology.org/2024.findings-acl.145</url>
    </location>
    <part>
        <date>2024-08</date>
        <extent unit="page">
            <start>2474</start>
            <end>2488</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T LM-Cocktail: Resilient Tuning of Language Models via Model Merging
%A Xiao, Shitao
%A Liu, Zheng
%A Zhang, Peitian
%A Xing, Xingrun
%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 xiao-etal-2024-lm
%X The pre-trained language models are continually fine-tuned to better support downstream applications. However, this operation may result in significant performance degeneration on general tasks beyond the targeted domain. To overcome this problem, we propose LM-Cocktail which enables the fine-tuned model to stay resilient in general perspectives. Our method is conducted in the form of model merging, where the fine-tuned language model is merged with the pre-trained base model or the peer models from other domains through weighted average. Despite simplicity, LM-Cocktail is surprisingly effective: the resulted model is able to achieve a strong empirical performance in the whole scope of general tasks while preserving a superior capacity in its targeted domain.
%U https://aclanthology.org/2024.findings-acl.145
%P 2474-2488

Markdown (Informal)

[LM-Cocktail: Resilient Tuning of Language Models via Model Merging](https://aclanthology.org/2024.findings-acl.145) (Xiao et al., Findings 2024)

• LM-Cocktail: Resilient Tuning of Language Models via Model Merging (Xiao et al., Findings 2024)

ACL

• Shitao Xiao, Zheng Liu, Peitian Zhang, and Xingrun Xing. 2024. LM-Cocktail: Resilient Tuning of Language Models via Model Merging. In Findings of the Association for Computational Linguistics ACL 2024, pages 2474–2488, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.