@article{han-kim-2026-cure,
title = "{CURE}: Cultural Value-based Reasoning for Enhancing the Cultural Adaptability of Large Language Models",
author = "Han, Mirae and
Kim, Harksoo",
journal = "Transactions of the Association for Computational Linguistics",
volume = "14",
year = "2026",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/2026.tacl-1.97/",
doi = "10.1162/tacl.a.795",
pages = "2145--2162",
abstract = "While large language models (LLMs) are widely used across cultures, they often generate culturally inappropriate responses in unfamiliar cultural contexts due to biases embedded in their training data. Existing approaches primarily rely on expanding static cultural knowledge, which fails to capture the inherently relative and context-dependent nature of culture. In this paper, we propose a Cultural value-based Reasoning (CURE) framework that interprets behaviors through underlying cultural value systems. In addition, we integrate CURE into LLMs via Chain-of-Thought (CoT) distillation, referred to as CURE-distillation, to internalize culturally grounded reasoning. Experimental results show that models trained with CURE-distillation improve cultural adaptability, enabling them to produce culturally aligned ethical judgments across diverse cultural scenarios. These results suggest that strengthening sociocultural reasoning capabilities can substantially improve the cultural adaptability of LLMs. The code is available at https://github.com/KUNLP/CURE."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="han-kim-2026-cure">
<titleInfo>
<title>CURE: Cultural Value-based Reasoning for Enhancing the Cultural Adaptability of Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mirae</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harksoo</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Transactions of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>While large language models (LLMs) are widely used across cultures, they often generate culturally inappropriate responses in unfamiliar cultural contexts due to biases embedded in their training data. Existing approaches primarily rely on expanding static cultural knowledge, which fails to capture the inherently relative and context-dependent nature of culture. In this paper, we propose a Cultural value-based Reasoning (CURE) framework that interprets behaviors through underlying cultural value systems. In addition, we integrate CURE into LLMs via Chain-of-Thought (CoT) distillation, referred to as CURE-distillation, to internalize culturally grounded reasoning. Experimental results show that models trained with CURE-distillation improve cultural adaptability, enabling them to produce culturally aligned ethical judgments across diverse cultural scenarios. These results suggest that strengthening sociocultural reasoning capabilities can substantially improve the cultural adaptability of LLMs. The code is available at https://github.com/KUNLP/CURE.</abstract>
<identifier type="citekey">han-kim-2026-cure</identifier>
<identifier type="doi">10.1162/tacl.a.795</identifier>
<location>
<url>https://aclanthology.org/2026.tacl-1.97/</url>
</location>
<part>
<date>2026</date>
<detail type="volume"><number>14</number></detail>
<extent unit="page">
<start>2145</start>
<end>2162</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T CURE: Cultural Value-based Reasoning for Enhancing the Cultural Adaptability of Large Language Models
%A Han, Mirae
%A Kim, Harksoo
%J Transactions of the Association for Computational Linguistics
%D 2026
%V 14
%I MIT Press
%C Cambridge, MA
%F han-kim-2026-cure
%X While large language models (LLMs) are widely used across cultures, they often generate culturally inappropriate responses in unfamiliar cultural contexts due to biases embedded in their training data. Existing approaches primarily rely on expanding static cultural knowledge, which fails to capture the inherently relative and context-dependent nature of culture. In this paper, we propose a Cultural value-based Reasoning (CURE) framework that interprets behaviors through underlying cultural value systems. In addition, we integrate CURE into LLMs via Chain-of-Thought (CoT) distillation, referred to as CURE-distillation, to internalize culturally grounded reasoning. Experimental results show that models trained with CURE-distillation improve cultural adaptability, enabling them to produce culturally aligned ethical judgments across diverse cultural scenarios. These results suggest that strengthening sociocultural reasoning capabilities can substantially improve the cultural adaptability of LLMs. The code is available at https://github.com/KUNLP/CURE.
%R 10.1162/tacl.a.795
%U https://aclanthology.org/2026.tacl-1.97/
%U https://doi.org/10.1162/tacl.a.795
%P 2145-2162
Markdown (Informal)
[CURE: Cultural Value-based Reasoning for Enhancing the Cultural Adaptability of Large Language Models](https://aclanthology.org/2026.tacl-1.97/) (Han & Kim, TACL 2026)
ACL