@inproceedings{wallat-etal-2025-study,
title = "A Study into Investigating Temporal Robustness of {LLM}s",
author = "Wallat, Jonas and
Abdallah, Abdelrahman and
Jatowt, Adam and
Anand, Avishek",
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.810/",
doi = "10.18653/v1/2025.findings-acl.810",
pages = "15685--15705",
ISBN = "979-8-89176-256-5",
abstract = "Large Language Models (LLMs) encapsulate a surprising amount of factual world knowledge. However, their performance on temporal questions and historical knowledge is limited because they often cannot understand temporal scope and orientation or neglect the temporal aspect altogether.In this study, we aim to measure precisely how robust LLMs are for question answering based on their ability to process temporal information and perform tasks requiring temporal reasoning and temporal factual knowledge. Specifically, we design eight time-sensitiverobustness tests for factual information to check the sensitivity of six popular LLMs in the zero-shot setting.Overall, we find LLMs lacking temporal robustness, especially to temporal reformulations and the use of different granularities of temporal references. We show how a selection of these eight tests can be used automatically to judge a model{'}s temporal robustness for user questions on the fly. Finally, we apply the findings of this study to improve the temporal QA performance by up to 55{\%}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wallat-etal-2025-study">
<titleInfo>
<title>A Study into Investigating Temporal Robustness of LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jonas</namePart>
<namePart type="family">Wallat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdelrahman</namePart>
<namePart type="family">Abdallah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Jatowt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Avishek</namePart>
<namePart type="family">Anand</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>Large Language Models (LLMs) encapsulate a surprising amount of factual world knowledge. However, their performance on temporal questions and historical knowledge is limited because they often cannot understand temporal scope and orientation or neglect the temporal aspect altogether.In this study, we aim to measure precisely how robust LLMs are for question answering based on their ability to process temporal information and perform tasks requiring temporal reasoning and temporal factual knowledge. Specifically, we design eight time-sensitiverobustness tests for factual information to check the sensitivity of six popular LLMs in the zero-shot setting.Overall, we find LLMs lacking temporal robustness, especially to temporal reformulations and the use of different granularities of temporal references. We show how a selection of these eight tests can be used automatically to judge a model’s temporal robustness for user questions on the fly. Finally, we apply the findings of this study to improve the temporal QA performance by up to 55%.</abstract>
<identifier type="citekey">wallat-etal-2025-study</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.810</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.810/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>15685</start>
<end>15705</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Study into Investigating Temporal Robustness of LLMs
%A Wallat, Jonas
%A Abdallah, Abdelrahman
%A Jatowt, Adam
%A Anand, Avishek
%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 wallat-etal-2025-study
%X Large Language Models (LLMs) encapsulate a surprising amount of factual world knowledge. However, their performance on temporal questions and historical knowledge is limited because they often cannot understand temporal scope and orientation or neglect the temporal aspect altogether.In this study, we aim to measure precisely how robust LLMs are for question answering based on their ability to process temporal information and perform tasks requiring temporal reasoning and temporal factual knowledge. Specifically, we design eight time-sensitiverobustness tests for factual information to check the sensitivity of six popular LLMs in the zero-shot setting.Overall, we find LLMs lacking temporal robustness, especially to temporal reformulations and the use of different granularities of temporal references. We show how a selection of these eight tests can be used automatically to judge a model’s temporal robustness for user questions on the fly. Finally, we apply the findings of this study to improve the temporal QA performance by up to 55%.
%R 10.18653/v1/2025.findings-acl.810
%U https://aclanthology.org/2025.findings-acl.810/
%U https://doi.org/10.18653/v1/2025.findings-acl.810
%P 15685-15705
Markdown (Informal)
[A Study into Investigating Temporal Robustness of LLMs](https://aclanthology.org/2025.findings-acl.810/) (Wallat et al., Findings 2025)
ACL
- Jonas Wallat, Abdelrahman Abdallah, Adam Jatowt, and Avishek Anand. 2025. A Study into Investigating Temporal Robustness of LLMs. In Findings of the Association for Computational Linguistics: ACL 2025, pages 15685–15705, Vienna, Austria. Association for Computational Linguistics.