@inproceedings{yari-koto-2025-unveiling,
title = "Unveiling Cultural Blind Spots: Analyzing the Limitations of m{LLM}s in Procedural Text Comprehension",
author = "Yari, Amir Hossein and
Koto, Fajri",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.987/",
doi = "10.18653/v1/2025.acl-long.987",
pages = "20151--20170",
ISBN = "979-8-89176-251-0",
abstract = "Despite the impressive performance of multilingual large language models (mLLMs) in various natural language processing tasks, their ability to understand procedural texts, particularly those with culture-specific content, remains largely unexplored. Texts describing cultural procedures, including rituals, traditional craftsmanship, and social etiquette, require an inherent understanding of cultural context, presenting a significant challenge for mLLMs. In this work, we introduce CAPTex, a benchmark designed to evaluate mLLMs' ability to process and reason over culturally diverse procedural texts in multiple languages. Using a range of evaluation methods, we find that (1) mLLMs struggle with culturally contextualized procedural content, particularly in low-resource languages; (2) performance varies across cultural domains, with some proving more difficult than others; and (3) models perform better on multiple-choice tasks presented in conversational formats than on direct questions. These results highlight the current limitations of mLLMs and emphasize the need for culturally informed benchmarks like CAPTex to support more accurate and inclusive language understanding."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yari-koto-2025-unveiling">
<titleInfo>
<title>Unveiling Cultural Blind Spots: Analyzing the Limitations of mLLMs in Procedural Text Comprehension</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="given">Hossein</namePart>
<namePart type="family">Yari</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>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>Despite the impressive performance of multilingual large language models (mLLMs) in various natural language processing tasks, their ability to understand procedural texts, particularly those with culture-specific content, remains largely unexplored. Texts describing cultural procedures, including rituals, traditional craftsmanship, and social etiquette, require an inherent understanding of cultural context, presenting a significant challenge for mLLMs. In this work, we introduce CAPTex, a benchmark designed to evaluate mLLMs’ ability to process and reason over culturally diverse procedural texts in multiple languages. Using a range of evaluation methods, we find that (1) mLLMs struggle with culturally contextualized procedural content, particularly in low-resource languages; (2) performance varies across cultural domains, with some proving more difficult than others; and (3) models perform better on multiple-choice tasks presented in conversational formats than on direct questions. These results highlight the current limitations of mLLMs and emphasize the need for culturally informed benchmarks like CAPTex to support more accurate and inclusive language understanding.</abstract>
<identifier type="citekey">yari-koto-2025-unveiling</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.987</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.987/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>20151</start>
<end>20170</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unveiling Cultural Blind Spots: Analyzing the Limitations of mLLMs in Procedural Text Comprehension
%A Yari, Amir Hossein
%A Koto, Fajri
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F yari-koto-2025-unveiling
%X Despite the impressive performance of multilingual large language models (mLLMs) in various natural language processing tasks, their ability to understand procedural texts, particularly those with culture-specific content, remains largely unexplored. Texts describing cultural procedures, including rituals, traditional craftsmanship, and social etiquette, require an inherent understanding of cultural context, presenting a significant challenge for mLLMs. In this work, we introduce CAPTex, a benchmark designed to evaluate mLLMs’ ability to process and reason over culturally diverse procedural texts in multiple languages. Using a range of evaluation methods, we find that (1) mLLMs struggle with culturally contextualized procedural content, particularly in low-resource languages; (2) performance varies across cultural domains, with some proving more difficult than others; and (3) models perform better on multiple-choice tasks presented in conversational formats than on direct questions. These results highlight the current limitations of mLLMs and emphasize the need for culturally informed benchmarks like CAPTex to support more accurate and inclusive language understanding.
%R 10.18653/v1/2025.acl-long.987
%U https://aclanthology.org/2025.acl-long.987/
%U https://doi.org/10.18653/v1/2025.acl-long.987
%P 20151-20170
Markdown (Informal)
[Unveiling Cultural Blind Spots: Analyzing the Limitations of mLLMs in Procedural Text Comprehension](https://aclanthology.org/2025.acl-long.987/) (Yari & Koto, ACL 2025)
ACL