<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="diera-etal-2026-rethinking">
    <titleInfo>
        <title>Rethinking Pivot Programming Languages in Code Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Andor</namePart>
        <namePart type="family">Diera</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lukas</namePart>
        <namePart type="family">Galke Poech</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Matthias</namePart>
        <namePart type="family">Tichy</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>Multilingual code language models transfer skills across programming languages (PLs), but whether any PL occupies a privileged pivot position remains contested: geometric analyses point to C-family languages and Go, while behavioral evidence highlights Python. We revisit this question under controls for representational anisotropy and length variation across PLs, two confounds that compromise prior cosine-based analyses. Across three code models on multilingual competitive-programming data, we study three views of cross-PL organization: pairwise PL geometry, PL-English alignment, and pivoted retrieval through candidate PL representation spaces. The results are relation-dependent. Code-code geometry reveals structured language regions but no universal center; code-English alignment favors high-level scripting languages; and pivoted retrieval favors different intermediate spaces for code-to-code and English-to-code transfer. These findings suggest that Python’s special role is better understood as English-facing affinity than as universal geometric centrality.</abstract>
    <identifier type="citekey">diera-etal-2026-rethinking</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1395/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>31875</start>
            <end>31892</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Rethinking Pivot Programming Languages in Code Language Models
%A Diera, Andor
%A Galke Poech, Lukas
%A Tichy, Matthias
%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 diera-etal-2026-rethinking
%X Multilingual code language models transfer skills across programming languages (PLs), but whether any PL occupies a privileged pivot position remains contested: geometric analyses point to C-family languages and Go, while behavioral evidence highlights Python. We revisit this question under controls for representational anisotropy and length variation across PLs, two confounds that compromise prior cosine-based analyses. Across three code models on multilingual competitive-programming data, we study three views of cross-PL organization: pairwise PL geometry, PL-English alignment, and pivoted retrieval through candidate PL representation spaces. The results are relation-dependent. Code-code geometry reveals structured language regions but no universal center; code-English alignment favors high-level scripting languages; and pivoted retrieval favors different intermediate spaces for code-to-code and English-to-code transfer. These findings suggest that Python’s special role is better understood as English-facing affinity than as universal geometric centrality.
%U https://aclanthology.org/2026.emnlp-main.1395/
%P 31875-31892

Markdown (Informal)

[Rethinking Pivot Programming Languages in Code Language Models](https://aclanthology.org/2026.emnlp-main.1395/) (Diera et al., EMNLP 2026)

• Rethinking Pivot Programming Languages in Code Language Models (Diera et al., EMNLP 2026)

ACL

• Andor Diera, Lukas Galke Poech, and Matthias Tichy. 2026. Rethinking Pivot Programming Languages in Code Language Models. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 31875–31892, Budapest, Hungary. Association for Computational Linguistics.