@inproceedings{tsutsumi-jinnai-2025-large,
title = "Do Large Language Models Know Folktales? A Case Study of Yokai in {J}apanese Folktales",
author = "Tsutsumi, Ayuto and
Jinnai, Yuu",
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.829/",
doi = "10.18653/v1/2025.findings-acl.829",
pages = "16124--16146",
ISBN = "979-8-89176-256-5",
abstract = "Although Large Language Models (LLMs) have demonstrated strong language understanding and generation abilities across various languages, their cultural knowledge is often limited to English-speaking communities, which can marginalize the cultures of non-English communities. To address the problem, the evaluation of the cultural awareness of the LLMs and the methods to develop culturally aware LLMs have been investigated. In this study, we focus on evaluating knowledge of folktales, a key medium for conveying and circulating culture. In particular, we focus on Japanese folktales, specifically on knowledge of Yokai. Yokai are supernatural creatures originating from Japanese folktales that continue to be popular motifs in art and entertainment today. Yokai have long served as a medium for cultural expression, making them an ideal subject for assessing the cultural awareness of LLMs. We introduce YokaiEval, a benchmark dataset consisting of 809 multiple-choice questions (each with four options) designed to probe knowledge about yokai. We evaluate the performance of 31 Japanese and multilingual LLMs on this dataset. The results show that models trained with Japanese language resources achieve higher accuracy than English-centric models, with those that underwent continued pretraining in Japanese, particularly those based on Llama-3, performing especially well."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tsutsumi-jinnai-2025-large">
<titleInfo>
<title>Do Large Language Models Know Folktales? A Case Study of Yokai in Japanese Folktales</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ayuto</namePart>
<namePart type="family">Tsutsumi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuu</namePart>
<namePart type="family">Jinnai</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>Although Large Language Models (LLMs) have demonstrated strong language understanding and generation abilities across various languages, their cultural knowledge is often limited to English-speaking communities, which can marginalize the cultures of non-English communities. To address the problem, the evaluation of the cultural awareness of the LLMs and the methods to develop culturally aware LLMs have been investigated. In this study, we focus on evaluating knowledge of folktales, a key medium for conveying and circulating culture. In particular, we focus on Japanese folktales, specifically on knowledge of Yokai. Yokai are supernatural creatures originating from Japanese folktales that continue to be popular motifs in art and entertainment today. Yokai have long served as a medium for cultural expression, making them an ideal subject for assessing the cultural awareness of LLMs. We introduce YokaiEval, a benchmark dataset consisting of 809 multiple-choice questions (each with four options) designed to probe knowledge about yokai. We evaluate the performance of 31 Japanese and multilingual LLMs on this dataset. The results show that models trained with Japanese language resources achieve higher accuracy than English-centric models, with those that underwent continued pretraining in Japanese, particularly those based on Llama-3, performing especially well.</abstract>
<identifier type="citekey">tsutsumi-jinnai-2025-large</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.829</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.829/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>16124</start>
<end>16146</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Do Large Language Models Know Folktales? A Case Study of Yokai in Japanese Folktales
%A Tsutsumi, Ayuto
%A Jinnai, Yuu
%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 tsutsumi-jinnai-2025-large
%X Although Large Language Models (LLMs) have demonstrated strong language understanding and generation abilities across various languages, their cultural knowledge is often limited to English-speaking communities, which can marginalize the cultures of non-English communities. To address the problem, the evaluation of the cultural awareness of the LLMs and the methods to develop culturally aware LLMs have been investigated. In this study, we focus on evaluating knowledge of folktales, a key medium for conveying and circulating culture. In particular, we focus on Japanese folktales, specifically on knowledge of Yokai. Yokai are supernatural creatures originating from Japanese folktales that continue to be popular motifs in art and entertainment today. Yokai have long served as a medium for cultural expression, making them an ideal subject for assessing the cultural awareness of LLMs. We introduce YokaiEval, a benchmark dataset consisting of 809 multiple-choice questions (each with four options) designed to probe knowledge about yokai. We evaluate the performance of 31 Japanese and multilingual LLMs on this dataset. The results show that models trained with Japanese language resources achieve higher accuracy than English-centric models, with those that underwent continued pretraining in Japanese, particularly those based on Llama-3, performing especially well.
%R 10.18653/v1/2025.findings-acl.829
%U https://aclanthology.org/2025.findings-acl.829/
%U https://doi.org/10.18653/v1/2025.findings-acl.829
%P 16124-16146
Markdown (Informal)
[Do Large Language Models Know Folktales? A Case Study of Yokai in Japanese Folktales](https://aclanthology.org/2025.findings-acl.829/) (Tsutsumi & Jinnai, Findings 2025)
ACL