<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="he-etal-2025-self">
    <titleInfo>
        <title>Self-Correction is More than Refinement: A Learning Framework for Visual and Language Reasoning Tasks</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jiayi</namePart>
        <namePart type="family">He</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hehai</namePart>
        <namePart type="family">Lin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Qingyun</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yi</namePart>
        <namePart type="given">R</namePart>
        <namePart type="family">Fung</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Heng</namePart>
        <namePart type="family">Ji</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>Findings of the Association for Computational Linguistics: ACL 2025</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">979-8-89176-256-5</identifier>
    </relatedItem>
    <abstract>While Vision-Language Models (VLMs) have shown remarkable abilities, they invariably generate flawed responses. Self-correction that instructs models to refine their outputs presents a promising solution to this issue. Previous studies have mainly concentrated on Large Language Models (LLMs), while the self-correction abilities of VLMs, particularly concerning both visual and linguistic information, remain largely unexamined. This study investigates the self-correction capabilities of VLMs during both inference and fine-tuning stages. We introduce a Self-Correction Learning (SCL) approach that enables VLMs to learn from their self-generated self-correction data through Direct Preference Optimization (DPO) without relying on external feedback, facilitating self-improvement. Experimental results demonstrate that although VLMs struggle to self-correct effectively during iterative inference without additional fine-tuning and external feedback, they can enhance their performance and avoid previous mistakes through preference fine-tuning when their generated self-correction data are categorized into preferred and disfavored samples. This study emphasizes that self-correction is not merely a refinement process; rather, it should enhance models’ reasoning ability through additional training, enabling them to generate high-quality responses directly without further refinement.</abstract>
    <identifier type="citekey">he-etal-2025-self</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-acl.331</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-acl.331/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>6405</start>
            <end>6421</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Self-Correction is More than Refinement: A Learning Framework for Visual and Language Reasoning Tasks
%A He, Jiayi
%A Lin, Hehai
%A Wang, Qingyun
%A Fung, Yi R.
%A Ji, Heng
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F he-etal-2025-self
%X While Vision-Language Models (VLMs) have shown remarkable abilities, they invariably generate flawed responses. Self-correction that instructs models to refine their outputs presents a promising solution to this issue. Previous studies have mainly concentrated on Large Language Models (LLMs), while the self-correction abilities of VLMs, particularly concerning both visual and linguistic information, remain largely unexamined. This study investigates the self-correction capabilities of VLMs during both inference and fine-tuning stages. We introduce a Self-Correction Learning (SCL) approach that enables VLMs to learn from their self-generated self-correction data through Direct Preference Optimization (DPO) without relying on external feedback, facilitating self-improvement. Experimental results demonstrate that although VLMs struggle to self-correct effectively during iterative inference without additional fine-tuning and external feedback, they can enhance their performance and avoid previous mistakes through preference fine-tuning when their generated self-correction data are categorized into preferred and disfavored samples. This study emphasizes that self-correction is not merely a refinement process; rather, it should enhance models’ reasoning ability through additional training, enabling them to generate high-quality responses directly without further refinement.
%R 10.18653/v1/2025.findings-acl.331
%U https://aclanthology.org/2025.findings-acl.331/
%U https://doi.org/10.18653/v1/2025.findings-acl.331
%P 6405-6421

Markdown (Informal)

[Self-Correction is More than Refinement: A Learning Framework for Visual and Language Reasoning Tasks](https://aclanthology.org/2025.findings-acl.331/) (He et al., Findings 2025)

• Self-Correction is More than Refinement: A Learning Framework for Visual and Language Reasoning Tasks (He et al., Findings 2025)

ACL

• Jiayi He, Hehai Lin, Qingyun Wang, Yi R. Fung, and Heng Ji. 2025. Self-Correction is More than Refinement: A Learning Framework for Visual and Language Reasoning Tasks. In Findings of the Association for Computational Linguistics: ACL 2025, pages 6405–6421, Vienna, Austria. Association for Computational Linguistics.