@inproceedings{chu-etal-2024-timebench,
title = "{T}ime{B}ench: A Comprehensive Evaluation of Temporal Reasoning Abilities in Large Language Models",
author = "Chu, Zheng and
Chen, Jingchang and
Chen, Qianglong and
Yu, Weijiang and
Wang, Haotian and
Liu, Ming and
Qin, Bing",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.66",
pages = "1204--1228",
abstract = "Grasping the concept of time is a fundamental facet of human cognition, indispensable for truly comprehending the intricacies of the world.Previous studies typically focus on specific aspects of time, lacking a comprehensive temporal reasoning benchmark.To address this, we propose TimeBench, a comprehensive hierarchical temporal reasoning benchmark that covers a broad spectrum of temporal reasoning phenomena.TimeBench provides a thorough evaluation for investigating the temporal reasoning capabilities of large language models.We conduct extensive experiments on GPT-4, LLaMA2, and other popular LLMs under various settings.Our experimental results indicate a significant performance gap between the state-of-the-art LLMs and humans, highlighting that there is still a considerable distance to cover in temporal reasoning.Besides, LLMs exhibit capability discrepancies across different reasoning categories.Furthermore, we thoroughly analyze the impact of multiple aspects on temporal reasoning and emphasize the associated challenges.We aspire for TimeBench to serve as a comprehensive benchmark, fostering research in temporal reasoning.Code and data are available at https://github.com/zchuz/TimeBench.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chu-etal-2024-timebench">
<titleInfo>
<title>TimeBench: A Comprehensive Evaluation of Temporal Reasoning Abilities in Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Chu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingchang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qianglong</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weijiang</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haotian</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bing</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Grasping the concept of time is a fundamental facet of human cognition, indispensable for truly comprehending the intricacies of the world.Previous studies typically focus on specific aspects of time, lacking a comprehensive temporal reasoning benchmark.To address this, we propose TimeBench, a comprehensive hierarchical temporal reasoning benchmark that covers a broad spectrum of temporal reasoning phenomena.TimeBench provides a thorough evaluation for investigating the temporal reasoning capabilities of large language models.We conduct extensive experiments on GPT-4, LLaMA2, and other popular LLMs under various settings.Our experimental results indicate a significant performance gap between the state-of-the-art LLMs and humans, highlighting that there is still a considerable distance to cover in temporal reasoning.Besides, LLMs exhibit capability discrepancies across different reasoning categories.Furthermore, we thoroughly analyze the impact of multiple aspects on temporal reasoning and emphasize the associated challenges.We aspire for TimeBench to serve as a comprehensive benchmark, fostering research in temporal reasoning.Code and data are available at https://github.com/zchuz/TimeBench.</abstract>
<identifier type="citekey">chu-etal-2024-timebench</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.66</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>1204</start>
<end>1228</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TimeBench: A Comprehensive Evaluation of Temporal Reasoning Abilities in Large Language Models
%A Chu, Zheng
%A Chen, Jingchang
%A Chen, Qianglong
%A Yu, Weijiang
%A Wang, Haotian
%A Liu, Ming
%A Qin, Bing
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F chu-etal-2024-timebench
%X Grasping the concept of time is a fundamental facet of human cognition, indispensable for truly comprehending the intricacies of the world.Previous studies typically focus on specific aspects of time, lacking a comprehensive temporal reasoning benchmark.To address this, we propose TimeBench, a comprehensive hierarchical temporal reasoning benchmark that covers a broad spectrum of temporal reasoning phenomena.TimeBench provides a thorough evaluation for investigating the temporal reasoning capabilities of large language models.We conduct extensive experiments on GPT-4, LLaMA2, and other popular LLMs under various settings.Our experimental results indicate a significant performance gap between the state-of-the-art LLMs and humans, highlighting that there is still a considerable distance to cover in temporal reasoning.Besides, LLMs exhibit capability discrepancies across different reasoning categories.Furthermore, we thoroughly analyze the impact of multiple aspects on temporal reasoning and emphasize the associated challenges.We aspire for TimeBench to serve as a comprehensive benchmark, fostering research in temporal reasoning.Code and data are available at https://github.com/zchuz/TimeBench.
%U https://aclanthology.org/2024.acl-long.66
%P 1204-1228
Markdown (Informal)
[TimeBench: A Comprehensive Evaluation of Temporal Reasoning Abilities in Large Language Models](https://aclanthology.org/2024.acl-long.66) (Chu et al., ACL 2024)
ACL