<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="honda-oka-2025-exploring">
    <titleInfo>
        <title>Exploring Explanations Improves the Robustness of In-Context Learning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ukyo</namePart>
        <namePart type="family">Honda</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tatsushi</namePart>
        <namePart type="family">Oka</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Wanxiang</namePart>
            <namePart type="family">Che</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joyce</namePart>
            <namePart type="family">Nabende</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ekaterina</namePart>
            <namePart type="family">Shutova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohammad</namePart>
            <namePart type="given">Taher</namePart>
            <namePart type="family">Pilehvar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-251-0</identifier>
    </relatedItem>
    <abstract>In-context learning (ICL) has emerged as a successful paradigm for leveraging large language models (LLMs). However, it often struggles to generalize beyond the distribution of the provided demonstrations. A recent advancement in enhancing robustness is ICL with explanations (X-ICL), which improves prediction reliability by guiding LLMs to understand and articulate the reasoning behind correct labels. Building on this approach, we introduce an advanced framework that extends X-ICL by systematically exploring explanations for all possible labels (X²-ICL), thereby enabling more comprehensive and robust decision-making. Experimental results on multiple natural language understanding datasets validate the effectiveness of X²-ICL, demonstrating significantly improved robustness to out-of-distribution data compared to the existing ICL approaches.</abstract>
    <identifier type="citekey">honda-oka-2025-exploring</identifier>
    <identifier type="doi">10.18653/v1/2025.acl-long.1155</identifier>
    <location>
        <url>https://aclanthology.org/2025.acl-long.1155/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>23693</start>
            <end>23714</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Exploring Explanations Improves the Robustness of In-Context Learning
%A Honda, Ukyo
%A Oka, Tatsushi
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F honda-oka-2025-exploring
%X In-context learning (ICL) has emerged as a successful paradigm for leveraging large language models (LLMs). However, it often struggles to generalize beyond the distribution of the provided demonstrations. A recent advancement in enhancing robustness is ICL with explanations (X-ICL), which improves prediction reliability by guiding LLMs to understand and articulate the reasoning behind correct labels. Building on this approach, we introduce an advanced framework that extends X-ICL by systematically exploring explanations for all possible labels (X²-ICL), thereby enabling more comprehensive and robust decision-making. Experimental results on multiple natural language understanding datasets validate the effectiveness of X²-ICL, demonstrating significantly improved robustness to out-of-distribution data compared to the existing ICL approaches.
%R 10.18653/v1/2025.acl-long.1155
%U https://aclanthology.org/2025.acl-long.1155/
%U https://doi.org/10.18653/v1/2025.acl-long.1155
%P 23693-23714

Markdown (Informal)

[Exploring Explanations Improves the Robustness of In-Context Learning](https://aclanthology.org/2025.acl-long.1155/) (Honda & Oka, ACL 2025)

• Exploring Explanations Improves the Robustness of In-Context Learning (Honda & Oka, ACL 2025)

ACL

• Ukyo Honda and Tatsushi Oka. 2025. Exploring Explanations Improves the Robustness of In-Context Learning. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 23693–23714, Vienna, Austria. Association for Computational Linguistics.