<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ryu-etal-2026-dont">
    <titleInfo>
        <title>Don’t Count the Edits, Judge by the Outcome Alone: Reward-Based Evaluation for Grammatical Error Correction</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Hayeong</namePart>
        <namePart type="family">Ryu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sunhee</namePart>
        <namePart type="family">Jo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Seunguk</namePart>
        <namePart type="family">Yu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">YoungBin</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>Grammatical error correction (GEC) evaluation has traditionally relied on reference or edit overlap, which can penalize valid rewrites that differ from gold corrections. Reference-free metrics reduce this dependence, but evaluating whether a fluent output is a valid correction of the source remains challenging. We propose SURE, a source-conditioned reward evaluator trained on within-source preferences spanning minimal-edit and rewrite-oriented corrections. SURE jointly learns an overall reward with criteria-level supervision for grammaticality, faithfulness, and fluency, together with span-level grounding for source-side error resolution. Experiments on SEEDA show that SURE performs competitively against strong baselines, with particular gains on rewrite-style corrections and more disentangled criteria-level diagnostics. Our code is available at https://github.com/hayeonggg/SURE.</abstract>
    <identifier type="citekey">ryu-etal-2026-dont</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.311/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>6581</start>
            <end>6597</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Don’t Count the Edits, Judge by the Outcome Alone: Reward-Based Evaluation for Grammatical Error Correction
%A Ryu, Hayeong
%A Jo, Sunhee
%A Yu, Seunguk
%A Kim, YoungBin
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F ryu-etal-2026-dont
%X Grammatical error correction (GEC) evaluation has traditionally relied on reference or edit overlap, which can penalize valid rewrites that differ from gold corrections. Reference-free metrics reduce this dependence, but evaluating whether a fluent output is a valid correction of the source remains challenging. We propose SURE, a source-conditioned reward evaluator trained on within-source preferences spanning minimal-edit and rewrite-oriented corrections. SURE jointly learns an overall reward with criteria-level supervision for grammaticality, faithfulness, and fluency, together with span-level grounding for source-side error resolution. Experiments on SEEDA show that SURE performs competitively against strong baselines, with particular gains on rewrite-style corrections and more disentangled criteria-level diagnostics. Our code is available at https://github.com/hayeonggg/SURE.
%U https://aclanthology.org/2026.findings-emnlp.311/
%P 6581-6597

Markdown (Informal)

[Don’t Count the Edits, Judge by the Outcome Alone: Reward-Based Evaluation for Grammatical Error Correction](https://aclanthology.org/2026.findings-emnlp.311/) (Ryu et al., Findings 2026)

• Don’t Count the Edits, Judge by the Outcome Alone: Reward-Based Evaluation for Grammatical Error Correction (Ryu et al., Findings 2026)

ACL

• Hayeong Ryu, Sunhee Jo, Seunguk Yu, and YoungBin Kim. 2026. Don’t Count the Edits, Judge by the Outcome Alone: Reward-Based Evaluation for Grammatical Error Correction. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 6581–6597, Budapest, Hungary. Association for Computational Linguistics.