<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bohra-bohra-2026-multilingual">
    <titleInfo>
        <title>Do Multilingual Encoders Produce Language-Consistent Semantic IDs?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Abhinav</namePart>
        <namePart type="family">Bohra</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Anuj</namePart>
        <namePart type="family">Bohra</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 10th Widening NLP Workshop</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Chen</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Emily</namePart>
            <namePart type="family">Allaway</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Meryem</namePart>
            <namePart type="family">M’hamdi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Peerat</namePart>
            <namePart type="family">Limkonchotiwat</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Richard</namePart>
            <namePart type="given">He</namePart>
            <namePart type="family">Bai</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Santosh</namePart>
            <namePart type="family">T.Y.S.S.</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Surendrabikram</namePart>
            <namePart type="family">Thapa</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yinqiao</namePart>
            <namePart type="family">Li</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">979-8-89176-472-9</identifier>
    </relatedItem>
    <abstract>Semantic IDs (SIDs) compress item embeddings into discrete code sequences used as the item vocabulary in generative retrieval. If the encoder is multilingual, it is tempting to assume the resulting SIDs are language-agnostic. We test this assumption on Amazon ESCI dataset (CITATION) rendered in English, Spanish, and Japanese. It fails at two separate points. Multilingual E5 places translations of the same product measurably apart, and residual quantization converts that displacement into a discrete prefix failure: under an English-heavy fit, a Japanese translation recovers the first SID code of its English counterpart in only 7.7% of cases, against 89.0% for an English rewording. A product-directed control shows the quantizer does not selectively increase language directions, instead the damage originates in the encoder. Most surprisingly, fitting the quantizer on a balanced language mixture makes cross-lingual agreement worse, not better, even as it equalizes codebook use. An English only fit preserves the first code for 67.6% of Spanish translations, the balanced fit preserves it for 6.6%. The results show that multilingual exposure alone does not buy consistent SIDs across languages. Cross-lingual SID agreement has to be optimized directly, or retrieval must tolerate code variation.</abstract>
    <identifier type="citekey">bohra-bohra-2026-multilingual</identifier>
    <location>
        <url>https://aclanthology.org/2026.winlp-main.12/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>121</start>
            <end>127</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Do Multilingual Encoders Produce Language-Consistent Semantic IDs?
%A Bohra, Abhinav
%A Bohra, Anuj
%Y Zhang, Chen
%Y Allaway, Emily
%Y M’hamdi, Meryem
%Y Limkonchotiwat, Peerat
%Y Bai, Richard He
%Y T.Y.S.S., Santosh
%Y Thapa, Surendrabikram
%Y Li, Yinqiao
%S Proceedings of the 10th Widening NLP Workshop
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-472-9
%F bohra-bohra-2026-multilingual
%X Semantic IDs (SIDs) compress item embeddings into discrete code sequences used as the item vocabulary in generative retrieval. If the encoder is multilingual, it is tempting to assume the resulting SIDs are language-agnostic. We test this assumption on Amazon ESCI dataset (CITATION) rendered in English, Spanish, and Japanese. It fails at two separate points. Multilingual E5 places translations of the same product measurably apart, and residual quantization converts that displacement into a discrete prefix failure: under an English-heavy fit, a Japanese translation recovers the first SID code of its English counterpart in only 7.7% of cases, against 89.0% for an English rewording. A product-directed control shows the quantizer does not selectively increase language directions, instead the damage originates in the encoder. Most surprisingly, fitting the quantizer on a balanced language mixture makes cross-lingual agreement worse, not better, even as it equalizes codebook use. An English only fit preserves the first code for 67.6% of Spanish translations, the balanced fit preserves it for 6.6%. The results show that multilingual exposure alone does not buy consistent SIDs across languages. Cross-lingual SID agreement has to be optimized directly, or retrieval must tolerate code variation.
%U https://aclanthology.org/2026.winlp-main.12/
%P 121-127

Markdown (Informal)

[Do Multilingual Encoders Produce Language-Consistent Semantic IDs?](https://aclanthology.org/2026.winlp-main.12/) (Bohra & Bohra, WiNLP 2026)

• Do Multilingual Encoders Produce Language-Consistent Semantic IDs? (Bohra & Bohra, WiNLP 2026)

ACL

• Abhinav Bohra and Anuj Bohra. 2026. Do Multilingual Encoders Produce Language-Consistent Semantic IDs?. In Proceedings of the 10th Widening NLP Workshop, pages 121–127, Budapest, Hungary. Association for Computational Linguistics.