<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2025-instruct">
    <titleInfo>
        <title>Instruct-of-Reflection: Enhancing Large Language Models Iterative Reflection Capabilities via Dynamic-Meta Instruction</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Liping</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chunhong</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Likang</namePart>
        <namePart type="family">Wu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chuang</namePart>
        <namePart type="family">Zhao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zheng</namePart>
        <namePart type="family">Hu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ming</namePart>
        <namePart type="family">He</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jianping</namePart>
        <namePart type="family">Fan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-04</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Luis</namePart>
            <namePart type="family">Chiruzzo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alan</namePart>
            <namePart type="family">Ritter</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lu</namePart>
            <namePart type="family">Wang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Albuquerque, New Mexico</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-189-6</identifier>
    </relatedItem>
    <abstract>Self-reflection for Large LanguageModels (LLMs) has gained significant attention. Existing approaches involve models iterating and improving their previous responses based on LLMs’ internal reflection ability or external feedback. However, recent research has raised doubts about whether intrinsic self-correction without external feedback may even degrade performance. Based on our empirical evidence, we find that current static reflection methods may lead to redundant, drift, and stubborn issues. To mitigate this, we introduce **I**nstruct-**o**f-**R**eflec**t**ion (**IoRT**), a novel and general reflection framework that leverages dynamic-meta instruction to enhance the iterative reflection capability of LLMs. Specifically, we propose the instructor driven by the meta-thoughts and self-consistency classifier, generates various instructions, including refresh, stop, and select, to guide the next reflection iteration. Our experiments demonstrate that IoRT achieves an average improvement of 10.1% over established baselines in mathematical and commonsense reasoning tasks, highlighting its efficacy and applicability. Our code is available at https://github.com/llp635/IoRT.</abstract>
    <identifier type="citekey">liu-etal-2025-instruct</identifier>
    <identifier type="doi">10.18653/v1/2025.naacl-long.502</identifier>
    <location>
        <url>https://aclanthology.org/2025.naacl-long.502/</url>
    </location>
    <part>
        <date>2025-04</date>
        <extent unit="page">
            <start>9956</start>
            <end>9978</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Instruct-of-Reflection: Enhancing Large Language Models Iterative Reflection Capabilities via Dynamic-Meta Instruction
%A Liu, Liping
%A Zhang, Chunhong
%A Wu, Likang
%A Zhao, Chuang
%A Hu, Zheng
%A He, Ming
%A Fan, Jianping
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F liu-etal-2025-instruct
%X Self-reflection for Large LanguageModels (LLMs) has gained significant attention. Existing approaches involve models iterating and improving their previous responses based on LLMs’ internal reflection ability or external feedback. However, recent research has raised doubts about whether intrinsic self-correction without external feedback may even degrade performance. Based on our empirical evidence, we find that current static reflection methods may lead to redundant, drift, and stubborn issues. To mitigate this, we introduce **I**nstruct-**o**f-**R**eflec**t**ion (**IoRT**), a novel and general reflection framework that leverages dynamic-meta instruction to enhance the iterative reflection capability of LLMs. Specifically, we propose the instructor driven by the meta-thoughts and self-consistency classifier, generates various instructions, including refresh, stop, and select, to guide the next reflection iteration. Our experiments demonstrate that IoRT achieves an average improvement of 10.1% over established baselines in mathematical and commonsense reasoning tasks, highlighting its efficacy and applicability. Our code is available at https://github.com/llp635/IoRT.
%R 10.18653/v1/2025.naacl-long.502
%U https://aclanthology.org/2025.naacl-long.502/
%U https://doi.org/10.18653/v1/2025.naacl-long.502
%P 9956-9978

Markdown (Informal)

[Instruct-of-Reflection: Enhancing Large Language Models Iterative Reflection Capabilities via Dynamic-Meta Instruction](https://aclanthology.org/2025.naacl-long.502/) (Liu et al., NAACL 2025)

• Instruct-of-Reflection: Enhancing Large Language Models Iterative Reflection Capabilities via Dynamic-Meta Instruction (Liu et al., NAACL 2025)

ACL

• Liping Liu, Chunhong Zhang, Likang Wu, Chuang Zhao, Zheng Hu, Ming He, and Jianping Fan. 2025. Instruct-of-Reflection: Enhancing Large Language Models Iterative Reflection Capabilities via Dynamic-Meta Instruction. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 9956–9978, Albuquerque, New Mexico. Association for Computational Linguistics.