<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pong-2026-post">
    <titleInfo>
        <title>Post-hoc Correction of Machine Translation Error Span Predictions</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Benjamin</namePart>
        <namePart type="family">Pong</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>Proceedings of the Eleventh Conference on Machine Translation</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Barry</namePart>
            <namePart type="family">Haddow</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tom</namePart>
            <namePart type="family">Kocmi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Philipp</namePart>
            <namePart type="family">Koehn</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Christof</namePart>
            <namePart type="family">Monz</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">979-8-89176-474-3</identifier>
    </relatedItem>
    <abstract>This paper presents an unsupervised quality estimation metric for machine translation that combines both neural and LLM models to identify and classify error spans for machine translations. As a submission to the WMT2026 Automated Evaluation Shared Task 1, this system builds on XCOMET-XL by applying offsets to the logits produced by the neural metric, post-hoc, to address the long-tailed probability problem, and uses an LLM as a second-stage to refine these predictions. Results show that XCOMET-XL with logits offset alone shows a boost in recall and character-level F1 scores for error span classifications across multiple language pairs, surpassing state-of-the-art baseline (i.e XCOMET-XL) and LLM-based approaches. This system also comprises a second-stage where a reasoning LLM-judge is employed to audit the error spans predicted by the logits-adjusted XCOMET metric, whose goal is to reduce spurious error classifications and improve overall precision. Results show that using LLM-judge to refine error spans provides no measurable improvements over predictions of the logits-adjusted XCOMET metric.</abstract>
    <identifier type="citekey">pong-2026-post</identifier>
    <location>
        <url>https://aclanthology.org/2026.wmt-main.106/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>1723</start>
            <end>1729</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Post-hoc Correction of Machine Translation Error Span Predictions
%A Pong, Benjamin
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Koehn, Philipp
%Y Monz, Christof
%S Proceedings of the Eleventh Conference on Machine Translation
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-474-3
%F pong-2026-post
%X This paper presents an unsupervised quality estimation metric for machine translation that combines both neural and LLM models to identify and classify error spans for machine translations. As a submission to the WMT2026 Automated Evaluation Shared Task 1, this system builds on XCOMET-XL by applying offsets to the logits produced by the neural metric, post-hoc, to address the long-tailed probability problem, and uses an LLM as a second-stage to refine these predictions. Results show that XCOMET-XL with logits offset alone shows a boost in recall and character-level F1 scores for error span classifications across multiple language pairs, surpassing state-of-the-art baseline (i.e XCOMET-XL) and LLM-based approaches. This system also comprises a second-stage where a reasoning LLM-judge is employed to audit the error spans predicted by the logits-adjusted XCOMET metric, whose goal is to reduce spurious error classifications and improve overall precision. Results show that using LLM-judge to refine error spans provides no measurable improvements over predictions of the logits-adjusted XCOMET metric.
%U https://aclanthology.org/2026.wmt-main.106/
%P 1723-1729

Markdown (Informal)

[Post-hoc Correction of Machine Translation Error Span Predictions](https://aclanthology.org/2026.wmt-main.106/) (Pong, WMT 2026)

• Post-hoc Correction of Machine Translation Error Span Predictions (Pong, WMT 2026)

ACL

• Benjamin Pong. 2026. Post-hoc Correction of Machine Translation Error Span Predictions. In Proceedings of the Eleventh Conference on Machine Translation, pages 1723–1729, Budapest, Hungary. Association for Computational Linguistics.