@inproceedings{sasaki-etal-2025-language,
title = "Can Language Models Handle a Non-Gregorian Calendar? The Case of the {J}apanese wareki",
author = "Sasaki, Mutsumi and
Kamoda, Go and
Takahashi, Ryosuke and
Sato, Kosuke and
Inui, Kentaro and
Sakaguchi, Keisuke and
Heinzerling, Benjamin",
editor = "Inui, Kentaro and
Sakti, Sakriani and
Wang, Haofen and
Wong, Derek F. and
Bhattacharyya, Pushpak and
Banerjee, Biplab and
Ekbal, Asif and
Chakraborty, Tanmoy and
Singh, Dhirendra Pratap",
booktitle = "Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "The Asian Federation of Natural Language Processing and The Association for Computational Linguistics",
url = "https://aclanthology.org/2025.ijcnlp-short.36/",
pages = "444--463",
ISBN = "979-8-89176-299-2",
abstract = "Temporal reasoning and knowledge are essential capabilities for language models (LMs).While much prior work has analyzed and improved temporal reasoning in LMs, most studies have focused solely on the Gregorian calendar.However, many non-Gregorian systems, such as the Japanese, Hijri, and Hebrew calendars, are in active use and reflect culturally grounded conceptions of time.If and how well current LMs can accurately handle such non-Gregorian calendars has not been evaluated so far.Here, we present a systematic evaluation of how well language models handle one such non-Gregorian system: the Japanese *wareki*.We create datasets that require temporal knowledge and reasoning in using *wareki* dates. Evaluating open and closed LMs, we find that some models can perform calendar conversions, but GPT-4o, Deepseek V3, and even Japanese-centric models struggle with Japanese calendar arithmetic and knowledge involving *wareki* dates.Error analysis suggests corpus frequency of Japanese calendar expressions and a Gregorian bias in the model{'}s knowledge as possible explanations.Our results show the importance of developing LMs that are better equipped for culture-specific tasks such as calendar understanding."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sasaki-etal-2025-language">
<titleInfo>
<title>Can Language Models Handle a Non-Gregorian Calendar? The Case of the Japanese wareki</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mutsumi</namePart>
<namePart type="family">Sasaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Go</namePart>
<namePart type="family">Kamoda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryosuke</namePart>
<namePart type="family">Takahashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kosuke</namePart>
<namePart type="family">Sato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</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">Benjamin</namePart>
<namePart type="family">Heinzerling</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haofen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biplab</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhirendra</namePart>
<namePart type="given">Pratap</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Asian Federation of Natural Language Processing and The Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-299-2</identifier>
</relatedItem>
<abstract>Temporal reasoning and knowledge are essential capabilities for language models (LMs).While much prior work has analyzed and improved temporal reasoning in LMs, most studies have focused solely on the Gregorian calendar.However, many non-Gregorian systems, such as the Japanese, Hijri, and Hebrew calendars, are in active use and reflect culturally grounded conceptions of time.If and how well current LMs can accurately handle such non-Gregorian calendars has not been evaluated so far.Here, we present a systematic evaluation of how well language models handle one such non-Gregorian system: the Japanese *wareki*.We create datasets that require temporal knowledge and reasoning in using *wareki* dates. Evaluating open and closed LMs, we find that some models can perform calendar conversions, but GPT-4o, Deepseek V3, and even Japanese-centric models struggle with Japanese calendar arithmetic and knowledge involving *wareki* dates.Error analysis suggests corpus frequency of Japanese calendar expressions and a Gregorian bias in the model’s knowledge as possible explanations.Our results show the importance of developing LMs that are better equipped for culture-specific tasks such as calendar understanding.</abstract>
<identifier type="citekey">sasaki-etal-2025-language</identifier>
<location>
<url>https://aclanthology.org/2025.ijcnlp-short.36/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>444</start>
<end>463</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Can Language Models Handle a Non-Gregorian Calendar? The Case of the Japanese wareki
%A Sasaki, Mutsumi
%A Kamoda, Go
%A Takahashi, Ryosuke
%A Sato, Kosuke
%A Inui, Kentaro
%A Sakaguchi, Keisuke
%A Heinzerling, Benjamin
%Y Inui, Kentaro
%Y Sakti, Sakriani
%Y Wang, Haofen
%Y Wong, Derek F.
%Y Bhattacharyya, Pushpak
%Y Banerjee, Biplab
%Y Ekbal, Asif
%Y Chakraborty, Tanmoy
%Y Singh, Dhirendra Pratap
%S Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics
%D 2025
%8 December
%I The Asian Federation of Natural Language Processing and The Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-299-2
%F sasaki-etal-2025-language
%X Temporal reasoning and knowledge are essential capabilities for language models (LMs).While much prior work has analyzed and improved temporal reasoning in LMs, most studies have focused solely on the Gregorian calendar.However, many non-Gregorian systems, such as the Japanese, Hijri, and Hebrew calendars, are in active use and reflect culturally grounded conceptions of time.If and how well current LMs can accurately handle such non-Gregorian calendars has not been evaluated so far.Here, we present a systematic evaluation of how well language models handle one such non-Gregorian system: the Japanese *wareki*.We create datasets that require temporal knowledge and reasoning in using *wareki* dates. Evaluating open and closed LMs, we find that some models can perform calendar conversions, but GPT-4o, Deepseek V3, and even Japanese-centric models struggle with Japanese calendar arithmetic and knowledge involving *wareki* dates.Error analysis suggests corpus frequency of Japanese calendar expressions and a Gregorian bias in the model’s knowledge as possible explanations.Our results show the importance of developing LMs that are better equipped for culture-specific tasks such as calendar understanding.
%U https://aclanthology.org/2025.ijcnlp-short.36/
%P 444-463
Markdown (Informal)
[Can Language Models Handle a Non-Gregorian Calendar? The Case of the Japanese wareki](https://aclanthology.org/2025.ijcnlp-short.36/) (Sasaki et al., IJCNLP-AACL 2025)
ACL
- Mutsumi Sasaki, Go Kamoda, Ryosuke Takahashi, Kosuke Sato, Kentaro Inui, Keisuke Sakaguchi, and Benjamin Heinzerling. 2025. Can Language Models Handle a Non-Gregorian Calendar? The Case of the Japanese wareki. In Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, pages 444–463, Mumbai, India. The Asian Federation of Natural Language Processing and The Association for Computational Linguistics.