@inproceedings{bharati-etal-2026-lost,
title = "Lost in Localization: Benchmarking Intralingual Cultural Adaptation in Large Language Models",
author = "Bharati, Soumedhik and
Brahma, Maharaj and
Desarkar, Maunendra Sankar",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1658/",
pages = "35338--35358",
ISBN = "979-8-89176-462-0",
abstract = "Cultural adaptation, rewriting text for a different cultural audience, requires more than lexical substitution. A model must decide what to change, whether each replacement is locally valid, and whether it preserves the original item{'}s functional role. We formalize this as function-preserving cultural transfer and introduce a dataset, a taxonomy, and an evaluation framework constructed around that principle. CulturalAdapt-6K identifies 6,000 culturally rich texts in four discourse domains, while the Cultural Rewriting and Adaptation Failure Taxonomy (CRAFT) classifies errors into five categories. To mitigate the Anglocentric priors of current models, our proposed framework anchors each culturally significant item in a Wikidata-linked function frame, capturing its contextual role rather than surface denotation. Across 191,968 adaptations by eight instruction-tuned LLMs, we find that the models that substitute the most are not the ones that substitute best. High localization increases failure exposure, while conservative retention increases validity scores, yet both converge to the same overall functional quality. Current generative models can certainly dress text in a target culture{'}s vocabulary but ultimately cannot reliably preserve the contextual roles the vocabulary is meant to serve."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bharati-etal-2026-lost">
<titleInfo>
<title>Lost in Localization: Benchmarking Intralingual Cultural Adaptation in Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Soumedhik</namePart>
<namePart type="family">Bharati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maharaj</namePart>
<namePart type="family">Brahma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maunendra</namePart>
<namePart type="given">Sankar</namePart>
<namePart type="family">Desarkar</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>Cultural adaptation, rewriting text for a different cultural audience, requires more than lexical substitution. A model must decide what to change, whether each replacement is locally valid, and whether it preserves the original item’s functional role. We formalize this as function-preserving cultural transfer and introduce a dataset, a taxonomy, and an evaluation framework constructed around that principle. CulturalAdapt-6K identifies 6,000 culturally rich texts in four discourse domains, while the Cultural Rewriting and Adaptation Failure Taxonomy (CRAFT) classifies errors into five categories. To mitigate the Anglocentric priors of current models, our proposed framework anchors each culturally significant item in a Wikidata-linked function frame, capturing its contextual role rather than surface denotation. Across 191,968 adaptations by eight instruction-tuned LLMs, we find that the models that substitute the most are not the ones that substitute best. High localization increases failure exposure, while conservative retention increases validity scores, yet both converge to the same overall functional quality. Current generative models can certainly dress text in a target culture’s vocabulary but ultimately cannot reliably preserve the contextual roles the vocabulary is meant to serve.</abstract>
<identifier type="citekey">bharati-etal-2026-lost</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1658/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>35338</start>
<end>35358</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Lost in Localization: Benchmarking Intralingual Cultural Adaptation in Large Language Models
%A Bharati, Soumedhik
%A Brahma, Maharaj
%A Desarkar, Maunendra Sankar
%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 bharati-etal-2026-lost
%X Cultural adaptation, rewriting text for a different cultural audience, requires more than lexical substitution. A model must decide what to change, whether each replacement is locally valid, and whether it preserves the original item’s functional role. We formalize this as function-preserving cultural transfer and introduce a dataset, a taxonomy, and an evaluation framework constructed around that principle. CulturalAdapt-6K identifies 6,000 culturally rich texts in four discourse domains, while the Cultural Rewriting and Adaptation Failure Taxonomy (CRAFT) classifies errors into five categories. To mitigate the Anglocentric priors of current models, our proposed framework anchors each culturally significant item in a Wikidata-linked function frame, capturing its contextual role rather than surface denotation. Across 191,968 adaptations by eight instruction-tuned LLMs, we find that the models that substitute the most are not the ones that substitute best. High localization increases failure exposure, while conservative retention increases validity scores, yet both converge to the same overall functional quality. Current generative models can certainly dress text in a target culture’s vocabulary but ultimately cannot reliably preserve the contextual roles the vocabulary is meant to serve.
%U https://aclanthology.org/2026.findings-emnlp.1658/
%P 35338-35358
Markdown (Informal)
[Lost in Localization: Benchmarking Intralingual Cultural Adaptation in Large Language Models](https://aclanthology.org/2026.findings-emnlp.1658/) (Bharati et al., Findings 2026)
ACL