<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mok-etal-2023-large">
    <titleInfo>
        <title>Large-scale Lifelong Learning of In-context Instructions and How to Tackle It</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jisoo</namePart>
        <namePart type="family">Mok</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jaeyoung</namePart>
        <namePart type="family">Do</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sungjin</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tara</namePart>
        <namePart type="family">Taghavi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Seunghak</namePart>
        <namePart type="family">Yu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sungroh</namePart>
        <namePart type="family">Yoon</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Rogers</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jordan</namePart>
            <namePart type="family">Boyd-Graber</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Naoaki</namePart>
            <namePart type="family">Okazaki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Toronto, Canada</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Jointly fine-tuning a Pre-trained Language Model (PLM) on a pre-defined set of tasks with in-context instructions has been proven to improve its generalization performance, allowing us to build a universal language model that can be deployed across task boundaries. In this work, we explore for the first time whether this attractive property of in-context instruction learning can be extended to a scenario in which tasks are fed to the target PLM in a sequential manner. The primary objective of so-called lifelong in-context instruction learning is to improve the target PLM’s instance- and task-level generalization performance as it observes more tasks. DynaInst, the proposed method to lifelong in-context instruction learning, achieves noticeable improvements in both types of generalization, nearly reaching the upper bound performance obtained through joint training.</abstract>
    <identifier type="citekey">mok-etal-2023-large</identifier>
    <identifier type="doi">10.18653/v1/2023.acl-long.703</identifier>
    <location>
        <url>https://aclanthology.org/2023.acl-long.703</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>12573</start>
            <end>12589</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Large-scale Lifelong Learning of In-context Instructions and How to Tackle It
%A Mok, Jisoo
%A Do, Jaeyoung
%A Lee, Sungjin
%A Taghavi, Tara
%A Yu, Seunghak
%A Yoon, Sungroh
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F mok-etal-2023-large
%X Jointly fine-tuning a Pre-trained Language Model (PLM) on a pre-defined set of tasks with in-context instructions has been proven to improve its generalization performance, allowing us to build a universal language model that can be deployed across task boundaries. In this work, we explore for the first time whether this attractive property of in-context instruction learning can be extended to a scenario in which tasks are fed to the target PLM in a sequential manner. The primary objective of so-called lifelong in-context instruction learning is to improve the target PLM’s instance- and task-level generalization performance as it observes more tasks. DynaInst, the proposed method to lifelong in-context instruction learning, achieves noticeable improvements in both types of generalization, nearly reaching the upper bound performance obtained through joint training.
%R 10.18653/v1/2023.acl-long.703
%U https://aclanthology.org/2023.acl-long.703
%U https://doi.org/10.18653/v1/2023.acl-long.703
%P 12573-12589

Markdown (Informal)

[Large-scale Lifelong Learning of In-context Instructions and How to Tackle It](https://aclanthology.org/2023.acl-long.703) (Mok et al., ACL 2023)

• Large-scale Lifelong Learning of In-context Instructions and How to Tackle It (Mok et al., ACL 2023)

ACL

• Jisoo Mok, Jaeyoung Do, Sungjin Lee, Tara Taghavi, Seunghak Yu, and Sungroh Yoon. 2023. Large-scale Lifelong Learning of In-context Instructions and How to Tackle It. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 12573–12589, Toronto, Canada. Association for Computational Linguistics.