@inproceedings{wang-etal-2026-benchmarking,
title = "Benchmarking Temporal Reasoning and Alignment Across {C}hinese Dynasties",
author = "Wang, Zhenglin and
Wu, Jialong and
Li, Pengfei and
Jiang, Yong and
Zhou, Deyu",
editor = "Demberg, Vera and
Inui, Kentaro and
Marquez, Llu{\'i}s",
booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 2: Short Papers)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eacl-short.6/",
pages = "105--120",
ISBN = "979-8-89176-381-4",
abstract = "Temporal reasoning is fundamental to human cognition and is crucial for various real-world applications. While recent advances in Large Language Models have demonstrated promising capabilities in temporal reasoning, existing benchmarks primarily rely on rule-based construction, lack contextual depth, and involve a limited range of temporal entities. To address these limitations, we introduce Chinese Time Reasoning (CTM), a benchmark designed to evaluate LLMs on temporal reasoning within the extensive scope of Chinese dynastic chronology. CTM emphasizes cross-entity relationships, pairwise temporal alignment, and contextualized and culturally-grounded reasoning, providing a comprehensive evaluation. Extensive experimental results reveal the challenges posed by CTM and highlight potential avenues for improvement."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-benchmarking">
<titleInfo>
<title>Benchmarking Temporal Reasoning and Alignment Across Chinese Dynasties</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhenglin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jialong</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pengfei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yong</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deyu</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Lluís</namePart>
<namePart type="family">Marquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-381-4</identifier>
</relatedItem>
<abstract>Temporal reasoning is fundamental to human cognition and is crucial for various real-world applications. While recent advances in Large Language Models have demonstrated promising capabilities in temporal reasoning, existing benchmarks primarily rely on rule-based construction, lack contextual depth, and involve a limited range of temporal entities. To address these limitations, we introduce Chinese Time Reasoning (CTM), a benchmark designed to evaluate LLMs on temporal reasoning within the extensive scope of Chinese dynastic chronology. CTM emphasizes cross-entity relationships, pairwise temporal alignment, and contextualized and culturally-grounded reasoning, providing a comprehensive evaluation. Extensive experimental results reveal the challenges posed by CTM and highlight potential avenues for improvement.</abstract>
<identifier type="citekey">wang-etal-2026-benchmarking</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-short.6/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>105</start>
<end>120</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Benchmarking Temporal Reasoning and Alignment Across Chinese Dynasties
%A Wang, Zhenglin
%A Wu, Jialong
%A Li, Pengfei
%A Jiang, Yong
%A Zhou, Deyu
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-381-4
%F wang-etal-2026-benchmarking
%X Temporal reasoning is fundamental to human cognition and is crucial for various real-world applications. While recent advances in Large Language Models have demonstrated promising capabilities in temporal reasoning, existing benchmarks primarily rely on rule-based construction, lack contextual depth, and involve a limited range of temporal entities. To address these limitations, we introduce Chinese Time Reasoning (CTM), a benchmark designed to evaluate LLMs on temporal reasoning within the extensive scope of Chinese dynastic chronology. CTM emphasizes cross-entity relationships, pairwise temporal alignment, and contextualized and culturally-grounded reasoning, providing a comprehensive evaluation. Extensive experimental results reveal the challenges posed by CTM and highlight potential avenues for improvement.
%U https://aclanthology.org/2026.eacl-short.6/
%P 105-120
Markdown (Informal)
[Benchmarking Temporal Reasoning and Alignment Across Chinese Dynasties](https://aclanthology.org/2026.eacl-short.6/) (Wang et al., EACL 2026)
ACL
- Zhenglin Wang, Jialong Wu, Pengfei Li, Yong Jiang, and Deyu Zhou. 2026. Benchmarking Temporal Reasoning and Alignment Across Chinese Dynasties. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers), pages 105–120, Rabat, Morocco. Association for Computational Linguistics.