Cross-Lingual LLM-Judge Transfer via Evaluation Decomposition

Ivaxi Sheth; Zeno Jonke; Amin Mantrach; Saab Mansour

Cross-Lingual LLM-Judge Transfer via Evaluation Decomposition

Ivaxi Sheth, Zeno Jonke, Amin Mantrach, Saab Mansour

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use ... for bold, ... for italic, ... for underline, <sc>...</sc> for small-caps, <tt>...<tt> for typewriter text, <url>...</url> for URLs, <a href=...> for hyperlinks, and <par/> for paragraph breaks.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

As large language models are increasingly deployed across diverse real-world applications, extending automated evaluation beyond English has become a critical challenge. Existing evaluation approaches are predominantly English-focused, and adapting them to other languages is hindered by the scarcity and cost of human-annotated judgments in most languages. We introduce a decomposition-based evaluation framework built around a Universal Criteria Set (UCS). UCS consists of a shared, language-agnostic set of evaluation dimensions, producing an interpretable intermediate representation that supports cross-lingual transfer with minimal supervision. Experiments on multiple faithfulness tasks across languages and model backbones demonstrate consistent improvements over strong baselines without requiring target-language annotations.

Anthology ID:: 2026.emnlp-main.1742
Volume:: Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
Month:: October
Year:: 2026
Address:: Budapest, Hungary
Editors:: Hung-Yi Lee, Sunipa Dev, Jessy Li, Desmond Elliott
Venue:: EMNLP
SIG:: SIGDAT
Publisher:: Association for Computational Linguistics
Note:
Pages:: 39727–39745
Language:
URL:: https://aclanthology.org/2026.emnlp-main.1742/
DOI:
Bibkey:
Cite (ACL):: Ivaxi Sheth, Zeno Jonke, Amin Mantrach, and Saab Mansour. 2026. Cross-Lingual LLM-Judge Transfer via Evaluation Decomposition. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 39727–39745, Budapest, Hungary. Association for Computational Linguistics.
Cite (Informal):: Cross-Lingual LLM-Judge Transfer via Evaluation Decomposition (Sheth et al., EMNLP 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.emnlp-main.1742.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{sheth-etal-2026-cross,
    title = "Cross-Lingual {LLM}-Judge Transfer via Evaluation Decomposition",
    author = "Sheth, Ivaxi  and
      Jonke, Zeno  and
      Mantrach, Amin  and
      Mansour, Saab",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.1742/",
    pages = "39727--39745",
    ISBN = "979-8-89176-459-0",
    abstract = "As large language models are increasingly deployed across diverse real-world applications, extending automated evaluation beyond English has become a critical challenge. Existing evaluation approaches are predominantly English-focused, and adapting them to other languages is hindered by the scarcity and cost of human-annotated judgments in most languages. We introduce a decomposition-based evaluation framework built around a Universal Criteria Set (UCS). UCS consists of a shared, language-agnostic set of evaluation dimensions, producing an interpretable intermediate representation that supports cross-lingual transfer with minimal supervision. Experiments on multiple faithfulness tasks across languages and model backbones demonstrate consistent improvements over strong baselines without requiring target-language annotations."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sheth-etal-2026-cross">
    <titleInfo>
        <title>Cross-Lingual LLM-Judge Transfer via Evaluation Decomposition</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ivaxi</namePart>
        <namePart type="family">Sheth</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zeno</namePart>
        <namePart type="family">Jonke</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Amin</namePart>
        <namePart type="family">Mantrach</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Saab</namePart>
        <namePart type="family">Mansour</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 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>As large language models are increasingly deployed across diverse real-world applications, extending automated evaluation beyond English has become a critical challenge. Existing evaluation approaches are predominantly English-focused, and adapting them to other languages is hindered by the scarcity and cost of human-annotated judgments in most languages. We introduce a decomposition-based evaluation framework built around a Universal Criteria Set (UCS). UCS consists of a shared, language-agnostic set of evaluation dimensions, producing an interpretable intermediate representation that supports cross-lingual transfer with minimal supervision. Experiments on multiple faithfulness tasks across languages and model backbones demonstrate consistent improvements over strong baselines without requiring target-language annotations.</abstract>
    <identifier type="citekey">sheth-etal-2026-cross</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1742/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>39727</start>
            <end>39745</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Cross-Lingual LLM-Judge Transfer via Evaluation Decomposition
%A Sheth, Ivaxi
%A Jonke, Zeno
%A Mantrach, Amin
%A Mansour, Saab
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F sheth-etal-2026-cross
%X As large language models are increasingly deployed across diverse real-world applications, extending automated evaluation beyond English has become a critical challenge. Existing evaluation approaches are predominantly English-focused, and adapting them to other languages is hindered by the scarcity and cost of human-annotated judgments in most languages. We introduce a decomposition-based evaluation framework built around a Universal Criteria Set (UCS). UCS consists of a shared, language-agnostic set of evaluation dimensions, producing an interpretable intermediate representation that supports cross-lingual transfer with minimal supervision. Experiments on multiple faithfulness tasks across languages and model backbones demonstrate consistent improvements over strong baselines without requiring target-language annotations.
%U https://aclanthology.org/2026.emnlp-main.1742/
%P 39727-39745

Download as File

Markdown (Informal)

[Cross-Lingual LLM-Judge Transfer via Evaluation Decomposition](https://aclanthology.org/2026.emnlp-main.1742/) (Sheth et al., EMNLP 2026)

Cross-Lingual LLM-Judge Transfer via Evaluation Decomposition (Sheth et al., EMNLP 2026)

ACL

Ivaxi Sheth, Zeno Jonke, Amin Mantrach, and Saab Mansour. 2026. Cross-Lingual LLM-Judge Transfer via Evaluation Decomposition. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 39727–39745, Budapest, Hungary. Association for Computational Linguistics.