<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shinto-etal-2025-extent">
    <titleInfo>
        <title>To What Extent Can In-Context Learning Solve Unseen Tasks?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ryoma</namePart>
        <namePart type="family">Shinto</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Masashi</namePart>
        <namePart type="family">Takeshita</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Rafal</namePart>
        <namePart type="family">Rzepka</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Toshihiko</namePart>
        <namePart type="family">Itoh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>The 14th International Joint Conference on Natural Language Processing and The 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Santosh</namePart>
            <namePart type="family">T.y.s.s</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Shuichiro</namePart>
            <namePart type="family">Shimizu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yifan</namePart>
            <namePart type="family">Gong</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Mumbai, India</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-304-3</identifier>
    </relatedItem>
    <abstract>While Large Language Models (LLMs) are known for their In-Context Learning (ICL) capabilities, there is no consensus on the underlying mechanisms. A key point of debate is whether ICL allows models to adapt to unseen tasks without parameter updates—that is, whether they can extrapolate. In this study, we address this question by constructing an arithmetic dataset based on the bivariate linear function z=ax+by to train a model and quantitatively evaluate its interpolation and extrapolation abilities through ICL. Our results show that while extrapolation was not achieved within our experimental design, tasks that were partially learned could be solved. We also found that the model acquires internal representations that can distinguish unseen tasks, and that greater task diversity in the training dataset improves ICL capabilities.</abstract>
    <identifier type="citekey">shinto-etal-2025-extent</identifier>
    <location>
        <url>https://aclanthology.org/2025.ijcnlp-srw.23/</url>
    </location>
    <part>
        <date>2025-12</date>
        <extent unit="page">
            <start>277</start>
            <end>288</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T To What Extent Can In-Context Learning Solve Unseen Tasks?
%A Shinto, Ryoma
%A Takeshita, Masashi
%A Rzepka, Rafal
%A Itoh, Toshihiko
%Y T.y.s.s, Santosh
%Y Shimizu, Shuichiro
%Y Gong, Yifan
%S The 14th International Joint Conference on Natural Language Processing and The 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics
%D 2025
%8 December
%I Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-304-3
%F shinto-etal-2025-extent
%X While Large Language Models (LLMs) are known for their In-Context Learning (ICL) capabilities, there is no consensus on the underlying mechanisms. A key point of debate is whether ICL allows models to adapt to unseen tasks without parameter updates—that is, whether they can extrapolate. In this study, we address this question by constructing an arithmetic dataset based on the bivariate linear function z=ax+by to train a model and quantitatively evaluate its interpolation and extrapolation abilities through ICL. Our results show that while extrapolation was not achieved within our experimental design, tasks that were partially learned could be solved. We also found that the model acquires internal representations that can distinguish unseen tasks, and that greater task diversity in the training dataset improves ICL capabilities.
%U https://aclanthology.org/2025.ijcnlp-srw.23/
%P 277-288

Markdown (Informal)

[To What Extent Can In-Context Learning Solve Unseen Tasks?](https://aclanthology.org/2025.ijcnlp-srw.23/) (Shinto et al., IJCNLP 2025)

• To What Extent Can In-Context Learning Solve Unseen Tasks? (Shinto et al., IJCNLP 2025)

ACL

• Ryoma Shinto, Masashi Takeshita, Rafal Rzepka, and Toshihiko Itoh. 2025. To What Extent Can In-Context Learning Solve Unseen Tasks?. In The 14th International Joint Conference on Natural Language Processing and The 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, pages 277–288, Mumbai, India. Association for Computational Linguistics.