@inproceedings{zaghouani-etal-2026-kz,
title = "{KZ}-{S}afety{P}rompts: A {K}azakh Safety Evaluation Prompt Dataset for Large Language Models",
author = "Zaghouani, Wajdi and
Ibrahim, Shimaa Amer and
Muratbek, Aruzhan and
Zhakenov, Olzhasbek and
Akhmetzhanova, Adiya",
editor = "Ojha, Atul Kr. and
Sakti, Sakriani and
Soria, Claudia and
Melero, Maite and
McCrae, John P. and
Lignos, Constantine and
Liu, Chao-Hong and
Claramunt, German Rigau and
Rehm, Georg",
booktitle = "Proceedings of the {SIGUL} 2026 Joint Workshop with {ELE}, {EURALI}, and {DCLRL}: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages",
month = may,
year = "2026",
address = "Palma, Mallorca, Spain",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.sigul-1.12/",
doi = "10.63317/322e8tcej745",
pages = "107--118",
abstract = "Kazakh is underrepresented in resources for evaluating the safety behavior of large language models. We present KZ-SafetyPrompts, a Kazakh prompt dataset for safety evaluation across eleven categories covering common risk areas such as self-harm, violence, child exploitation, sexual content, racist content, radicalization, and regulated goods or illegal activities. The dataset contains 5,717 prompts written natively in Kazakh (Cyrillic), organized by category, with English translations for cross-lingual analysis. Prompts resemble realistic user queries, often in a teen or child style, and are phrased as intent prompts without procedural instructions. We document the writing protocol, labeling procedures (including borderline-case decision rules), and quality-control steps (schema standardization, completeness checks, and deduplication). We also align the categories with widely used safety taxonomies to support integration with existing evaluation pipelines. Baseline results with GPT-4o show an overall refusal rate of 28.2{\%}, varying from 5.5{\%} to 53.8{\%} across categories, indicating that Kazakh prompts expose category-specific safety gaps not captured by English-only evaluation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zaghouani-etal-2026-kz">
<titleInfo>
<title>KZ-SafetyPrompts: A Kazakh Safety Evaluation Prompt Dataset for Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shimaa</namePart>
<namePart type="given">Amer</namePart>
<namePart type="family">Ibrahim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aruzhan</namePart>
<namePart type="family">Muratbek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Olzhasbek</namePart>
<namePart type="family">Zhakenov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adiya</namePart>
<namePart type="family">Akhmetzhanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the SIGUL 2026 Joint Workshop with ELE, EURALI, and DCLRL: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Soria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maite</namePart>
<namePart type="family">Melero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">P</namePart>
<namePart type="family">McCrae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Constantine</namePart>
<namePart type="family">Lignos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao-Hong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">German</namePart>
<namePart type="given">Rigau</namePart>
<namePart type="family">Claramunt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Kazakh is underrepresented in resources for evaluating the safety behavior of large language models. We present KZ-SafetyPrompts, a Kazakh prompt dataset for safety evaluation across eleven categories covering common risk areas such as self-harm, violence, child exploitation, sexual content, racist content, radicalization, and regulated goods or illegal activities. The dataset contains 5,717 prompts written natively in Kazakh (Cyrillic), organized by category, with English translations for cross-lingual analysis. Prompts resemble realistic user queries, often in a teen or child style, and are phrased as intent prompts without procedural instructions. We document the writing protocol, labeling procedures (including borderline-case decision rules), and quality-control steps (schema standardization, completeness checks, and deduplication). We also align the categories with widely used safety taxonomies to support integration with existing evaluation pipelines. Baseline results with GPT-4o show an overall refusal rate of 28.2%, varying from 5.5% to 53.8% across categories, indicating that Kazakh prompts expose category-specific safety gaps not captured by English-only evaluation.</abstract>
<identifier type="citekey">zaghouani-etal-2026-kz</identifier>
<identifier type="doi">10.63317/322e8tcej745</identifier>
<location>
<url>https://aclanthology.org/2026.sigul-1.12/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>107</start>
<end>118</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KZ-SafetyPrompts: A Kazakh Safety Evaluation Prompt Dataset for Large Language Models
%A Zaghouani, Wajdi
%A Ibrahim, Shimaa Amer
%A Muratbek, Aruzhan
%A Zhakenov, Olzhasbek
%A Akhmetzhanova, Adiya
%Y Ojha, Atul Kr.
%Y Sakti, Sakriani
%Y Soria, Claudia
%Y Melero, Maite
%Y McCrae, John P.
%Y Lignos, Constantine
%Y Liu, Chao-Hong
%Y Claramunt, German Rigau
%Y Rehm, Georg
%S Proceedings of the SIGUL 2026 Joint Workshop with ELE, EURALI, and DCLRL: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca, Spain
%F zaghouani-etal-2026-kz
%X Kazakh is underrepresented in resources for evaluating the safety behavior of large language models. We present KZ-SafetyPrompts, a Kazakh prompt dataset for safety evaluation across eleven categories covering common risk areas such as self-harm, violence, child exploitation, sexual content, racist content, radicalization, and regulated goods or illegal activities. The dataset contains 5,717 prompts written natively in Kazakh (Cyrillic), organized by category, with English translations for cross-lingual analysis. Prompts resemble realistic user queries, often in a teen or child style, and are phrased as intent prompts without procedural instructions. We document the writing protocol, labeling procedures (including borderline-case decision rules), and quality-control steps (schema standardization, completeness checks, and deduplication). We also align the categories with widely used safety taxonomies to support integration with existing evaluation pipelines. Baseline results with GPT-4o show an overall refusal rate of 28.2%, varying from 5.5% to 53.8% across categories, indicating that Kazakh prompts expose category-specific safety gaps not captured by English-only evaluation.
%R 10.63317/322e8tcej745
%U https://aclanthology.org/2026.sigul-1.12/
%U https://doi.org/10.63317/322e8tcej745
%P 107-118
Markdown (Informal)
[KZ-SafetyPrompts: A Kazakh Safety Evaluation Prompt Dataset for Large Language Models](https://aclanthology.org/2026.sigul-1.12/) (Zaghouani et al., SIGUL-EURALI-DCLRL 2026)
ACL
- Wajdi Zaghouani, Shimaa Amer Ibrahim, Aruzhan Muratbek, Olzhasbek Zhakenov, and Adiya Akhmetzhanova. 2026. KZ-SafetyPrompts: A Kazakh Safety Evaluation Prompt Dataset for Large Language Models. In Proceedings of the SIGUL 2026 Joint Workshop with ELE, EURALI, and DCLRL: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages, pages 107–118, Palma, Mallorca, Spain. ELRA Language Resources Association (ELRA).