@article{pawar-etal-2025-survey,
title = "Survey of Cultural Awareness in Language Models: Text and Beyond",
author = "Pawar, Siddhesh and
Park, Junyeong and
Jin, Jiho and
Arora, Arnav and
Myung, Junho and
Yadav, Srishti and
Haznitrama, Faiz Ghifari and
Song, Inhwa and
Oh, Alice and
Augenstein, Isabelle",
journal = "Computational Linguistics",
volume = "51",
number = "3",
month = sep,
year = "2025",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/2025.cl-3.7/",
doi = "10.1162/coli.a.14",
pages = "907--1004",
abstract = "Large-scale deployment of large language models (LLMs) in various applications, such as chatbots and virtual assistants, requires LLMs to be culturally sensitive to the user to ensure inclusivity. Culture has been widely studied in psychology and anthropology, and there has been a recent surge in research on making LLMs more culturally inclusive, going beyond multilinguality and building on findings from psychology and anthropology. In this article, we survey efforts towards incorporating cultural awareness into text-based and multimodal LLMs. We start by defining cultural awareness in LLMs, taking definitions of culture from the anthropology and psychology literature as a point of departure. We then examine methodologies adopted for creating cross-cultural datasets, strategies for cultural inclusion in downstream tasks, and methodologies that have been used for benchmarking cultural awareness in LLMs. Further, we discuss the ethical implications of cultural alignment, the role of human{--}computer interaction in driving cultural inclusion in LLMs, and the role of cultural alignment in driving social science research. We finally provide pointers to future research based on our findings about gaps in the literature.1"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pawar-etal-2025-survey">
<titleInfo>
<title>Survey of Cultural Awareness in Language Models: Text and Beyond</title>
</titleInfo>
<name type="personal">
<namePart type="given">Siddhesh</namePart>
<namePart type="family">Pawar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junyeong</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiho</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arnav</namePart>
<namePart type="family">Arora</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junho</namePart>
<namePart type="family">Myung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Srishti</namePart>
<namePart type="family">Yadav</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Faiz</namePart>
<namePart type="given">Ghifari</namePart>
<namePart type="family">Haznitrama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Inhwa</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alice</namePart>
<namePart type="family">Oh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>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>Large-scale deployment of large language models (LLMs) in various applications, such as chatbots and virtual assistants, requires LLMs to be culturally sensitive to the user to ensure inclusivity. Culture has been widely studied in psychology and anthropology, and there has been a recent surge in research on making LLMs more culturally inclusive, going beyond multilinguality and building on findings from psychology and anthropology. In this article, we survey efforts towards incorporating cultural awareness into text-based and multimodal LLMs. We start by defining cultural awareness in LLMs, taking definitions of culture from the anthropology and psychology literature as a point of departure. We then examine methodologies adopted for creating cross-cultural datasets, strategies for cultural inclusion in downstream tasks, and methodologies that have been used for benchmarking cultural awareness in LLMs. Further, we discuss the ethical implications of cultural alignment, the role of human–computer interaction in driving cultural inclusion in LLMs, and the role of cultural alignment in driving social science research. We finally provide pointers to future research based on our findings about gaps in the literature.1</abstract>
<identifier type="citekey">pawar-etal-2025-survey</identifier>
<identifier type="doi">10.1162/coli.a.14</identifier>
<location>
<url>https://aclanthology.org/2025.cl-3.7/</url>
</location>
<part>
<date>2025-09</date>
<detail type="volume"><number>51</number></detail>
<detail type="issue"><number>3</number></detail>
<extent unit="page">
<start>907</start>
<end>1004</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Survey of Cultural Awareness in Language Models: Text and Beyond
%A Pawar, Siddhesh
%A Park, Junyeong
%A Jin, Jiho
%A Arora, Arnav
%A Myung, Junho
%A Yadav, Srishti
%A Haznitrama, Faiz Ghifari
%A Song, Inhwa
%A Oh, Alice
%A Augenstein, Isabelle
%J Computational Linguistics
%D 2025
%8 September
%V 51
%N 3
%I MIT Press
%C Cambridge, MA
%F pawar-etal-2025-survey
%X Large-scale deployment of large language models (LLMs) in various applications, such as chatbots and virtual assistants, requires LLMs to be culturally sensitive to the user to ensure inclusivity. Culture has been widely studied in psychology and anthropology, and there has been a recent surge in research on making LLMs more culturally inclusive, going beyond multilinguality and building on findings from psychology and anthropology. In this article, we survey efforts towards incorporating cultural awareness into text-based and multimodal LLMs. We start by defining cultural awareness in LLMs, taking definitions of culture from the anthropology and psychology literature as a point of departure. We then examine methodologies adopted for creating cross-cultural datasets, strategies for cultural inclusion in downstream tasks, and methodologies that have been used for benchmarking cultural awareness in LLMs. Further, we discuss the ethical implications of cultural alignment, the role of human–computer interaction in driving cultural inclusion in LLMs, and the role of cultural alignment in driving social science research. We finally provide pointers to future research based on our findings about gaps in the literature.1
%R 10.1162/coli.a.14
%U https://aclanthology.org/2025.cl-3.7/
%U https://doi.org/10.1162/coli.a.14
%P 907-1004
Markdown (Informal)
[Survey of Cultural Awareness in Language Models: Text and Beyond](https://aclanthology.org/2025.cl-3.7/) (Pawar et al., CL 2025)
ACL
- Siddhesh Pawar, Junyeong Park, Jiho Jin, Arnav Arora, Junho Myung, Srishti Yadav, Faiz Ghifari Haznitrama, Inhwa Song, Alice Oh, and Isabelle Augenstein. 2025. Survey of Cultural Awareness in Language Models: Text and Beyond. Computational Linguistics, 51(3):907–1004.