@inproceedings{haneda-etal-2026-wikioriginqa,
title = "{W}iki{O}rigin{QA}: Automated Construction of a {QA} Dataset with Knowledge Origins for Analyzing Cultural Bias",
author = "Haneda, Kento and
Kishinami, Yosuke and
Fujii, Ryo and
Sakaguchi, Keisuke and
Morishita, Makoto",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 2: Short Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-short.6/",
pages = "69--77",
ISBN = "979-8-89176-440-8",
abstract = "Existing datasets on cultural knowledge have been typically created by human annotators familiar with each culture. However, the process requires considerable human effort, presenting a significant challenge to scalability. To address this challenge, we introduce WikiOriginQA, a QA dataset automatically constructed by objectively representing the origins of knowledge through the creation dates of different Wikipedia language editions. Experimental results with the created dataset confirm that LLM performance tends to be biased toward Anglophone cultures. These findings demonstrate the validity of our automated approach, enabling cultural bias evaluations with superior scalability across diverse languages without extensive manual annotation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="haneda-etal-2026-wikioriginqa">
<titleInfo>
<title>WikiOriginQA: Automated Construction of a QA Dataset with Knowledge Origins for Analyzing Cultural Bias</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kento</namePart>
<namePart type="family">Haneda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yosuke</namePart>
<namePart type="family">Kishinami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryo</namePart>
<namePart type="family">Fujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Keisuke</namePart>
<namePart type="family">Sakaguchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Makoto</namePart>
<namePart type="family">Morishita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-440-8</identifier>
</relatedItem>
<abstract>Existing datasets on cultural knowledge have been typically created by human annotators familiar with each culture. However, the process requires considerable human effort, presenting a significant challenge to scalability. To address this challenge, we introduce WikiOriginQA, a QA dataset automatically constructed by objectively representing the origins of knowledge through the creation dates of different Wikipedia language editions. Experimental results with the created dataset confirm that LLM performance tends to be biased toward Anglophone cultures. These findings demonstrate the validity of our automated approach, enabling cultural bias evaluations with superior scalability across diverse languages without extensive manual annotation.</abstract>
<identifier type="citekey">haneda-etal-2026-wikioriginqa</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-short.6/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>69</start>
<end>77</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WikiOriginQA: Automated Construction of a QA Dataset with Knowledge Origins for Analyzing Cultural Bias
%A Haneda, Kento
%A Kishinami, Yosuke
%A Fujii, Ryo
%A Sakaguchi, Keisuke
%A Morishita, Makoto
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-440-8
%F haneda-etal-2026-wikioriginqa
%X Existing datasets on cultural knowledge have been typically created by human annotators familiar with each culture. However, the process requires considerable human effort, presenting a significant challenge to scalability. To address this challenge, we introduce WikiOriginQA, a QA dataset automatically constructed by objectively representing the origins of knowledge through the creation dates of different Wikipedia language editions. Experimental results with the created dataset confirm that LLM performance tends to be biased toward Anglophone cultures. These findings demonstrate the validity of our automated approach, enabling cultural bias evaluations with superior scalability across diverse languages without extensive manual annotation.
%U https://aclanthology.org/2026.aacl-short.6/
%P 69-77
Markdown (Informal)
[WikiOriginQA: Automated Construction of a QA Dataset with Knowledge Origins for Analyzing Cultural Bias](https://aclanthology.org/2026.aacl-short.6/) (Haneda et al., AACL-IJCNLP 2026)
ACL