@inproceedings{chen-etal-2025-perceive,
title = "Perceive the Passage of Time: A Systematic Evaluation of Large Language Model in Temporal Relativity",
author = "Chen, Shuang and
Zheng, Yining and
Li, Shimin and
Cheng, Qinyuan and
Qiu, Xipeng",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.554/",
pages = "8304--8313",
abstract = "Temporal perception is crucial for Large Language Models(LLMs) to effectively understand the world. However, current benchmarks primarily focus on temporal reasoning, falling short in understanding the temporal characteristics involving temporal perception, particularly in understanding temporal relativity. In this paper, we introduce TempBench, a comprehensive benchmark designed to evaluate the temporal-relative ability of LLMs. TempBench encompasses 4 distinct scenarios: Physiology, Psychology, Cognition and Mixture. We conduct an extensive experiments on GPT-4, a series of Llama and other popular LLMs. The experiment results demonstrate a significant performance gap between LLMs and humans in temporal-relative capability. Furthermore, the error types of temporal-relative ability in LLMs are proposed to thoroughly analyze the impact of multiple aspects and emphasize the associated challenges. We anticipate that TempBench will drive further advancements in enhancing the temporal-perceiving capabilities of L"
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2025-perceive">
<titleInfo>
<title>Perceive the Passage of Time: A Systematic Evaluation of Large Language Model in Temporal Relativity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shuang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yining</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shimin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qinyuan</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xipeng</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Temporal perception is crucial for Large Language Models(LLMs) to effectively understand the world. However, current benchmarks primarily focus on temporal reasoning, falling short in understanding the temporal characteristics involving temporal perception, particularly in understanding temporal relativity. In this paper, we introduce TempBench, a comprehensive benchmark designed to evaluate the temporal-relative ability of LLMs. TempBench encompasses 4 distinct scenarios: Physiology, Psychology, Cognition and Mixture. We conduct an extensive experiments on GPT-4, a series of Llama and other popular LLMs. The experiment results demonstrate a significant performance gap between LLMs and humans in temporal-relative capability. Furthermore, the error types of temporal-relative ability in LLMs are proposed to thoroughly analyze the impact of multiple aspects and emphasize the associated challenges. We anticipate that TempBench will drive further advancements in enhancing the temporal-perceiving capabilities of L</abstract>
<identifier type="citekey">chen-etal-2025-perceive</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.554/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>8304</start>
<end>8313</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Perceive the Passage of Time: A Systematic Evaluation of Large Language Model in Temporal Relativity
%A Chen, Shuang
%A Zheng, Yining
%A Li, Shimin
%A Cheng, Qinyuan
%A Qiu, Xipeng
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F chen-etal-2025-perceive
%X Temporal perception is crucial for Large Language Models(LLMs) to effectively understand the world. However, current benchmarks primarily focus on temporal reasoning, falling short in understanding the temporal characteristics involving temporal perception, particularly in understanding temporal relativity. In this paper, we introduce TempBench, a comprehensive benchmark designed to evaluate the temporal-relative ability of LLMs. TempBench encompasses 4 distinct scenarios: Physiology, Psychology, Cognition and Mixture. We conduct an extensive experiments on GPT-4, a series of Llama and other popular LLMs. The experiment results demonstrate a significant performance gap between LLMs and humans in temporal-relative capability. Furthermore, the error types of temporal-relative ability in LLMs are proposed to thoroughly analyze the impact of multiple aspects and emphasize the associated challenges. We anticipate that TempBench will drive further advancements in enhancing the temporal-perceiving capabilities of L
%U https://aclanthology.org/2025.coling-main.554/
%P 8304-8313
Markdown (Informal)
[Perceive the Passage of Time: A Systematic Evaluation of Large Language Model in Temporal Relativity](https://aclanthology.org/2025.coling-main.554/) (Chen et al., COLING 2025)
ACL