@inproceedings{minggad-etal-2026-monculture,
title = "{M}on{C}ulture-Eval: A Hierarchical Benchmark for Evaluating {M}ongolian Cultural Capabilities of Large Language Models across Scripts and Regions",
author = "Minggad, Quulgan and
Zinan, Xiao and
Sun, Yuan",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.1449/",
pages = "28997--29014",
ISBN = "979-8-89176-395-1",
abstract = "While Large Language Models (LLMs) have achieved impressive linguistic fluency in low-resource languages, their capacity to process deep cultural nuances remains insufficiently quantified. This paper introduces MonCulture-Eval, a benchmark designed to assess the cultural intelligence of LLMs in the Mongolian context across two writing systems (Traditional and Cyrillic) and three regional sub-cultures (Alxa, Ordos, and Horqin). Curated entirely from primary, non-digitized archives to prevent data contamination, the benchmark employs a three-layer cognitive hierarchy{---}Factual, Situational, and Values{---}supplemented by specialized tasks including Riddles, Taboos, and Proverbs. Evaluation of frontier models reveals a severe ``Script Gap'' and a systematic ``Etic Bias,'' where models sanitize spiritual rituals into secular functional norms."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="minggad-etal-2026-monculture">
<titleInfo>
<title>MonCulture-Eval: A Hierarchical Benchmark for Evaluating Mongolian Cultural Capabilities of Large Language Models across Scripts and Regions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Quulgan</namePart>
<namePart type="family">Minggad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiao</namePart>
<namePart type="family">Zinan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuan</namePart>
<namePart type="family">Sun</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>Findings of the Association for Computational Linguistics: ACL 2026</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">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>While Large Language Models (LLMs) have achieved impressive linguistic fluency in low-resource languages, their capacity to process deep cultural nuances remains insufficiently quantified. This paper introduces MonCulture-Eval, a benchmark designed to assess the cultural intelligence of LLMs in the Mongolian context across two writing systems (Traditional and Cyrillic) and three regional sub-cultures (Alxa, Ordos, and Horqin). Curated entirely from primary, non-digitized archives to prevent data contamination, the benchmark employs a three-layer cognitive hierarchy—Factual, Situational, and Values—supplemented by specialized tasks including Riddles, Taboos, and Proverbs. Evaluation of frontier models reveals a severe “Script Gap” and a systematic “Etic Bias,” where models sanitize spiritual rituals into secular functional norms.</abstract>
<identifier type="citekey">minggad-etal-2026-monculture</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1449/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>28997</start>
<end>29014</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MonCulture-Eval: A Hierarchical Benchmark for Evaluating Mongolian Cultural Capabilities of Large Language Models across Scripts and Regions
%A Minggad, Quulgan
%A Zinan, Xiao
%A Sun, Yuan
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F minggad-etal-2026-monculture
%X While Large Language Models (LLMs) have achieved impressive linguistic fluency in low-resource languages, their capacity to process deep cultural nuances remains insufficiently quantified. This paper introduces MonCulture-Eval, a benchmark designed to assess the cultural intelligence of LLMs in the Mongolian context across two writing systems (Traditional and Cyrillic) and three regional sub-cultures (Alxa, Ordos, and Horqin). Curated entirely from primary, non-digitized archives to prevent data contamination, the benchmark employs a three-layer cognitive hierarchy—Factual, Situational, and Values—supplemented by specialized tasks including Riddles, Taboos, and Proverbs. Evaluation of frontier models reveals a severe “Script Gap” and a systematic “Etic Bias,” where models sanitize spiritual rituals into secular functional norms.
%U https://aclanthology.org/2026.findings-acl.1449/
%P 28997-29014
Markdown (Informal)
[MonCulture-Eval: A Hierarchical Benchmark for Evaluating Mongolian Cultural Capabilities of Large Language Models across Scripts and Regions](https://aclanthology.org/2026.findings-acl.1449/) (Minggad et al., Findings 2026)
ACL