@inproceedings{laiyk-etal-2026-stereotype,
title = "Stereotype Bias in a Bilingual Setting: A Culturally Grounded Evaluation in {K}azakhstan",
author = "Laiyk, Nurkhan and
Orel, Daniil and
Mussabayeva, Ayana and
Goloburda, Maiya and
Kuishibekova, Kamila and
Goloburda, Liya and
Turmakhan, Diana and
Nakov, Preslav and
Wang, Yuxia and
Koto, Fajri",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.598/",
pages = "13114--13131",
ISBN = "979-8-89176-390-6",
abstract = "Stereotype bias in language models has been widely examined in English, but remains largely understudied in bilingual contexts where multiple linguistic and cultural systems interact. This gap is especially important in regions where language use reflects complex historical and sociopolitical influences. In this work, we focus on Kazakhstan, a bilingual society where Kazakh, a low-resource Turkic language, and Russian, a high-resource Slavic language, are both actively used and frequently code-mixed in everyday communication. We introduce Aqbileq, a high-quality, human-verified dataset consisting of 5,634 stereotype-bearing statements in Kazakh, Russian, and code-mixed forms, covering six culturally salient domains. We evaluate both multilingual and Kazakh-specific language models using perplexity-based scoring and pretraining simulations, and find that stereotype bias is most pronounced in code-mixed inputs. Our results highlight the limitations of existing evaluation frameworks and emphasize the need for culturally grounded, linguistically inclusive benchmarks to better assess and mitigate bias in language models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="laiyk-etal-2026-stereotype">
<titleInfo>
<title>Stereotype Bias in a Bilingual Setting: A Culturally Grounded Evaluation in Kazakhstan</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nurkhan</namePart>
<namePart type="family">Laiyk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniil</namePart>
<namePart type="family">Orel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayana</namePart>
<namePart type="family">Mussabayeva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maiya</namePart>
<namePart type="family">Goloburda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kamila</namePart>
<namePart type="family">Kuishibekova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liya</namePart>
<namePart type="family">Goloburda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diana</namePart>
<namePart type="family">Turmakhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuxia</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fajri</namePart>
<namePart type="family">Koto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Stereotype bias in language models has been widely examined in English, but remains largely understudied in bilingual contexts where multiple linguistic and cultural systems interact. This gap is especially important in regions where language use reflects complex historical and sociopolitical influences. In this work, we focus on Kazakhstan, a bilingual society where Kazakh, a low-resource Turkic language, and Russian, a high-resource Slavic language, are both actively used and frequently code-mixed in everyday communication. We introduce Aqbileq, a high-quality, human-verified dataset consisting of 5,634 stereotype-bearing statements in Kazakh, Russian, and code-mixed forms, covering six culturally salient domains. We evaluate both multilingual and Kazakh-specific language models using perplexity-based scoring and pretraining simulations, and find that stereotype bias is most pronounced in code-mixed inputs. Our results highlight the limitations of existing evaluation frameworks and emphasize the need for culturally grounded, linguistically inclusive benchmarks to better assess and mitigate bias in language models.</abstract>
<identifier type="citekey">laiyk-etal-2026-stereotype</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.598/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>13114</start>
<end>13131</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Stereotype Bias in a Bilingual Setting: A Culturally Grounded Evaluation in Kazakhstan
%A Laiyk, Nurkhan
%A Orel, Daniil
%A Mussabayeva, Ayana
%A Goloburda, Maiya
%A Kuishibekova, Kamila
%A Goloburda, Liya
%A Turmakhan, Diana
%A Nakov, Preslav
%A Wang, Yuxia
%A Koto, Fajri
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F laiyk-etal-2026-stereotype
%X Stereotype bias in language models has been widely examined in English, but remains largely understudied in bilingual contexts where multiple linguistic and cultural systems interact. This gap is especially important in regions where language use reflects complex historical and sociopolitical influences. In this work, we focus on Kazakhstan, a bilingual society where Kazakh, a low-resource Turkic language, and Russian, a high-resource Slavic language, are both actively used and frequently code-mixed in everyday communication. We introduce Aqbileq, a high-quality, human-verified dataset consisting of 5,634 stereotype-bearing statements in Kazakh, Russian, and code-mixed forms, covering six culturally salient domains. We evaluate both multilingual and Kazakh-specific language models using perplexity-based scoring and pretraining simulations, and find that stereotype bias is most pronounced in code-mixed inputs. Our results highlight the limitations of existing evaluation frameworks and emphasize the need for culturally grounded, linguistically inclusive benchmarks to better assess and mitigate bias in language models.
%U https://aclanthology.org/2026.acl-long.598/
%P 13114-13131
Markdown (Informal)
[Stereotype Bias in a Bilingual Setting: A Culturally Grounded Evaluation in Kazakhstan](https://aclanthology.org/2026.acl-long.598/) (Laiyk et al., ACL 2026)
ACL
- Nurkhan Laiyk, Daniil Orel, Ayana Mussabayeva, Maiya Goloburda, Kamila Kuishibekova, Liya Goloburda, Diana Turmakhan, Preslav Nakov, Yuxia Wang, and Fajri Koto. 2026. Stereotype Bias in a Bilingual Setting: A Culturally Grounded Evaluation in Kazakhstan. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13114–13131, San Diego, California, United States. Association for Computational Linguistics.