@inproceedings{luo-etal-2025-etrqa,
title = "{ETRQA}: A Comprehensive Benchmark for Evaluating Event Temporal Reasoning Abilities of Large Language Models",
author = "Luo, Sigang and
Liu, Yinan and
Lin, Dongying and
Zhai, Yingying and
Wang, Bin and
Yang, Xiaochun and
Liu, Junpeng",
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.1198/",
doi = "10.18653/v1/2025.findings-acl.1198",
pages = "23321--23339",
ISBN = "979-8-89176-256-5",
abstract = "Event temporal reasoning (ETR) aims to model and reason about the relationships between events and time, as well as between events in the real world. Proficiency in ETR is a significant indicator that a large language model (LLM) truly understands the physical world. Previous question-answering datasets available for evaluating the ETR ability lack a systematic taxonomy and pay limited attention to compound questions. In this paper, we propose a unified taxonomy for event temporal questions and construct a comprehensive benchmark ETRQA, to evaluate the ETR abilities of LLMs based on this taxonomy. ETRQA not only inherits and expands the evaluation content of existing datasets but also contains multiple categories of compound questions. We evaluate two leading LLM series, Llama and Qwen, on ETRQA across various settings. Our experimental results indicate that large-scale LLMs exhibit certain ETR abilities. Yet they do not perform well in solving specific types of reasoning tasks, including reasoning involving time spans, reasoning for compound questions, and reasoning with fine temporal granularity. Additionally, we hope ETRQA can benefit the temporal reasoning research community for future studies."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="luo-etal-2025-etrqa">
<titleInfo>
<title>ETRQA: A Comprehensive Benchmark for Evaluating Event Temporal Reasoning Abilities of Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sigang</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yinan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongying</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yingying</namePart>
<namePart type="family">Zhai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaochun</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junpeng</namePart>
<namePart type="family">Liu</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>Event temporal reasoning (ETR) aims to model and reason about the relationships between events and time, as well as between events in the real world. Proficiency in ETR is a significant indicator that a large language model (LLM) truly understands the physical world. Previous question-answering datasets available for evaluating the ETR ability lack a systematic taxonomy and pay limited attention to compound questions. In this paper, we propose a unified taxonomy for event temporal questions and construct a comprehensive benchmark ETRQA, to evaluate the ETR abilities of LLMs based on this taxonomy. ETRQA not only inherits and expands the evaluation content of existing datasets but also contains multiple categories of compound questions. We evaluate two leading LLM series, Llama and Qwen, on ETRQA across various settings. Our experimental results indicate that large-scale LLMs exhibit certain ETR abilities. Yet they do not perform well in solving specific types of reasoning tasks, including reasoning involving time spans, reasoning for compound questions, and reasoning with fine temporal granularity. Additionally, we hope ETRQA can benefit the temporal reasoning research community for future studies.</abstract>
<identifier type="citekey">luo-etal-2025-etrqa</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.1198</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.1198/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>23321</start>
<end>23339</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ETRQA: A Comprehensive Benchmark for Evaluating Event Temporal Reasoning Abilities of Large Language Models
%A Luo, Sigang
%A Liu, Yinan
%A Lin, Dongying
%A Zhai, Yingying
%A Wang, Bin
%A Yang, Xiaochun
%A Liu, Junpeng
%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 luo-etal-2025-etrqa
%X Event temporal reasoning (ETR) aims to model and reason about the relationships between events and time, as well as between events in the real world. Proficiency in ETR is a significant indicator that a large language model (LLM) truly understands the physical world. Previous question-answering datasets available for evaluating the ETR ability lack a systematic taxonomy and pay limited attention to compound questions. In this paper, we propose a unified taxonomy for event temporal questions and construct a comprehensive benchmark ETRQA, to evaluate the ETR abilities of LLMs based on this taxonomy. ETRQA not only inherits and expands the evaluation content of existing datasets but also contains multiple categories of compound questions. We evaluate two leading LLM series, Llama and Qwen, on ETRQA across various settings. Our experimental results indicate that large-scale LLMs exhibit certain ETR abilities. Yet they do not perform well in solving specific types of reasoning tasks, including reasoning involving time spans, reasoning for compound questions, and reasoning with fine temporal granularity. Additionally, we hope ETRQA can benefit the temporal reasoning research community for future studies.
%R 10.18653/v1/2025.findings-acl.1198
%U https://aclanthology.org/2025.findings-acl.1198/
%U https://doi.org/10.18653/v1/2025.findings-acl.1198
%P 23321-23339
Markdown (Informal)
[ETRQA: A Comprehensive Benchmark for Evaluating Event Temporal Reasoning Abilities of Large Language Models](https://aclanthology.org/2025.findings-acl.1198/) (Luo et al., Findings 2025)
ACL