@inproceedings{kamruzzaman-etal-2025-banstereoset,
title = "{B}an{S}tereo{S}et: A Dataset to Measure Stereotypical Social Biases in {LLM}s for {B}angla",
author = "Kamruzzaman, Mahammed and
Monsur, Abdullah Al and
Das, Shrabon Kumar and
Hassan, Enamul and
Kim, Gene Louis",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.179/",
doi = "10.18653/v1/2025.findings-acl.179",
pages = "3450--3460",
ISBN = "979-8-89176-256-5",
abstract = "This study presents ***BanStereoSet***, a dataset designed to evaluate stereotypical social biases in multilingual LLMs for the Bangla language. In an effort to extend the focus of bias research beyond English-centric datasets, we have localized the content from the StereoSet, IndiBias, and kamruzzaman-etal{'}s datasets, producing a resource tailored to capture biases prevalent within the Bangla-speaking community. Our BanStereoSet dataset consists of 1,194 sentences spanning 9 categories of bias: race, profession, gender, ageism, beauty, beauty in profession, region, caste, and religion. This dataset not only serves as a crucial tool for measuring bias in multilingual LLMs but also facilitates the exploration of stereotypical bias across different social categories, potentially guiding the development of more equitable language technologies in *Bangladeshi* contexts. Our analysis of several language models using this dataset indicates significant biases, reinforcing the necessity for culturally and linguistically adapted datasets to develop more equitable language technologies."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kamruzzaman-etal-2025-banstereoset">
<titleInfo>
<title>BanStereoSet: A Dataset to Measure Stereotypical Social Biases in LLMs for Bangla</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mahammed</namePart>
<namePart type="family">Kamruzzaman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdullah</namePart>
<namePart type="given">Al</namePart>
<namePart type="family">Monsur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shrabon</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enamul</namePart>
<namePart type="family">Hassan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gene</namePart>
<namePart type="given">Louis</namePart>
<namePart type="family">Kim</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>Findings of the Association for Computational Linguistics: ACL 2025</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">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>This study presents ***BanStereoSet***, a dataset designed to evaluate stereotypical social biases in multilingual LLMs for the Bangla language. In an effort to extend the focus of bias research beyond English-centric datasets, we have localized the content from the StereoSet, IndiBias, and kamruzzaman-etal’s datasets, producing a resource tailored to capture biases prevalent within the Bangla-speaking community. Our BanStereoSet dataset consists of 1,194 sentences spanning 9 categories of bias: race, profession, gender, ageism, beauty, beauty in profession, region, caste, and religion. This dataset not only serves as a crucial tool for measuring bias in multilingual LLMs but also facilitates the exploration of stereotypical bias across different social categories, potentially guiding the development of more equitable language technologies in *Bangladeshi* contexts. Our analysis of several language models using this dataset indicates significant biases, reinforcing the necessity for culturally and linguistically adapted datasets to develop more equitable language technologies.</abstract>
<identifier type="citekey">kamruzzaman-etal-2025-banstereoset</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.179</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.179/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>3450</start>
<end>3460</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BanStereoSet: A Dataset to Measure Stereotypical Social Biases in LLMs for Bangla
%A Kamruzzaman, Mahammed
%A Monsur, Abdullah Al
%A Das, Shrabon Kumar
%A Hassan, Enamul
%A Kim, Gene Louis
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F kamruzzaman-etal-2025-banstereoset
%X This study presents ***BanStereoSet***, a dataset designed to evaluate stereotypical social biases in multilingual LLMs for the Bangla language. In an effort to extend the focus of bias research beyond English-centric datasets, we have localized the content from the StereoSet, IndiBias, and kamruzzaman-etal’s datasets, producing a resource tailored to capture biases prevalent within the Bangla-speaking community. Our BanStereoSet dataset consists of 1,194 sentences spanning 9 categories of bias: race, profession, gender, ageism, beauty, beauty in profession, region, caste, and religion. This dataset not only serves as a crucial tool for measuring bias in multilingual LLMs but also facilitates the exploration of stereotypical bias across different social categories, potentially guiding the development of more equitable language technologies in *Bangladeshi* contexts. Our analysis of several language models using this dataset indicates significant biases, reinforcing the necessity for culturally and linguistically adapted datasets to develop more equitable language technologies.
%R 10.18653/v1/2025.findings-acl.179
%U https://aclanthology.org/2025.findings-acl.179/
%U https://doi.org/10.18653/v1/2025.findings-acl.179
%P 3450-3460
Markdown (Informal)
[BanStereoSet: A Dataset to Measure Stereotypical Social Biases in LLMs for Bangla](https://aclanthology.org/2025.findings-acl.179/) (Kamruzzaman et al., Findings 2025)
ACL