@inproceedings{demir-etal-2026-timeres,
title = "{T}ime{R}es: A {T}urkish Benchmark For Evaluating Temporal Understanding of Large Language Models",
author = {Demir, Habib Ya{\u{g}}{\i}z and
Atlamaz, {\"U}mit and
{\"U}sk{\"u}darl{\i}, Susan},
editor = "Baez Santamaria, Selene and
Somayajula, Sai Ashish and
Yamaguchi, Atsuki",
booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 4: Student Research Workshop)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eacl-srw.67/",
pages = "910--920",
ISBN = "979-8-89176-383-8",
abstract = "Temporal information is an essential part of communication, and understanding language requires processing it effectively. Despite recent advances, Large Language Models (LLMs) still struggle with temporal understanding.Existing benchmarks primarily focus on English and underexplore how linguistic structure contributes to temporal meaning.As a result, temporal understanding in languages other than English remains largely understudied.In this paper, we introduce TimeRes, a Turkish benchmark for evaluating temporal understanding of LLMs. TimeRes aims to investigate comprehension of Reichenbach{'}s temporal points and reported speech through date arithmetic.Our dataset includes 4,600 questions across 4 tasks at two levels of complexity, and presents a paired question formulation to distinguish temporal discourse understanding from temporal arithmetic capabilities.We evaluated six LLMs, and demonstrated that models struggle to resolve reported speech and fail to generalize across word order variations."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="demir-etal-2026-timeres">
<titleInfo>
<title>TimeRes: A Turkish Benchmark For Evaluating Temporal Understanding of Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Habib</namePart>
<namePart type="given">Yağız</namePart>
<namePart type="family">Demir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ümit</namePart>
<namePart type="family">Atlamaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Susan</namePart>
<namePart type="family">Üsküdarlı</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 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Selene</namePart>
<namePart type="family">Baez Santamaria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sai</namePart>
<namePart type="given">Ashish</namePart>
<namePart type="family">Somayajula</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atsuki</namePart>
<namePart type="family">Yamaguchi</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">979-8-89176-383-8</identifier>
</relatedItem>
<abstract>Temporal information is an essential part of communication, and understanding language requires processing it effectively. Despite recent advances, Large Language Models (LLMs) still struggle with temporal understanding.Existing benchmarks primarily focus on English and underexplore how linguistic structure contributes to temporal meaning.As a result, temporal understanding in languages other than English remains largely understudied.In this paper, we introduce TimeRes, a Turkish benchmark for evaluating temporal understanding of LLMs. TimeRes aims to investigate comprehension of Reichenbach’s temporal points and reported speech through date arithmetic.Our dataset includes 4,600 questions across 4 tasks at two levels of complexity, and presents a paired question formulation to distinguish temporal discourse understanding from temporal arithmetic capabilities.We evaluated six LLMs, and demonstrated that models struggle to resolve reported speech and fail to generalize across word order variations.</abstract>
<identifier type="citekey">demir-etal-2026-timeres</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-srw.67/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>910</start>
<end>920</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TimeRes: A Turkish Benchmark For Evaluating Temporal Understanding of Large Language Models
%A Demir, Habib Yağız
%A Atlamaz, Ümit
%A Üsküdarlı, Susan
%Y Baez Santamaria, Selene
%Y Somayajula, Sai Ashish
%Y Yamaguchi, Atsuki
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-383-8
%F demir-etal-2026-timeres
%X Temporal information is an essential part of communication, and understanding language requires processing it effectively. Despite recent advances, Large Language Models (LLMs) still struggle with temporal understanding.Existing benchmarks primarily focus on English and underexplore how linguistic structure contributes to temporal meaning.As a result, temporal understanding in languages other than English remains largely understudied.In this paper, we introduce TimeRes, a Turkish benchmark for evaluating temporal understanding of LLMs. TimeRes aims to investigate comprehension of Reichenbach’s temporal points and reported speech through date arithmetic.Our dataset includes 4,600 questions across 4 tasks at two levels of complexity, and presents a paired question formulation to distinguish temporal discourse understanding from temporal arithmetic capabilities.We evaluated six LLMs, and demonstrated that models struggle to resolve reported speech and fail to generalize across word order variations.
%U https://aclanthology.org/2026.eacl-srw.67/
%P 910-920
Markdown (Informal)
[TimeRes: A Turkish Benchmark For Evaluating Temporal Understanding of Large Language Models](https://aclanthology.org/2026.eacl-srw.67/) (Demir et al., EACL 2026)
ACL