@inproceedings{ghaboura-etal-2025-time,
title = "Time Travel: A Comprehensive Benchmark to Evaluate {LMM}s on Historical and Cultural Artifacts",
author = "Ghaboura, Sara and
More, Ketan Pravin and
Thawkar, Ritesh and
Ghallabi, Wafa Al and
Thawakar, Omkar and
Khan, Fahad Shahbaz and
Cholakkal, Hisham and
Khan, Salman and
Anwer, Rao Muhammad",
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.1211/",
doi = "10.18653/v1/2025.findings-acl.1211",
pages = "23627--23641",
ISBN = "979-8-89176-256-5",
abstract = "Understanding historical and cultural artifacts demands human expertise and advanced computational techniques, yet the process remains complex and time-intensive. While large multimodal models offer promising support, their evaluation and improvement require a standardized benchmark. To address this, we introduce TimeTravel, a benchmark of 10,250 expert-verified samples spanning 266 distinct cultures across 10 major historical regions. Designed for AI-driven analysis of manuscripts, artworks, inscriptions, and archaeological discoveries, TimeTravel provides a structured dataset and robust evaluation framework to assess AI models' capabilities in classification, interpretation, and historical comprehension. By integrating AI with historical research, TimeTravel fosters AI-powered tools for historians, archaeologists, researchers, and cultural tourists to extract valuable insights while ensuring technology contributes meaningfully to historical discovery and cultural heritage preservation. We evaluate contemporary AI models on TimeTravel, highlighting their strengths and identifying areas for improvement. Our goal is to establish AI as a reliable partner in preserving cultural heritage, ensuring that technological advancements contribute meaningfully to historical discovery. We release the TimeTravel dataset and evaluation suite as open-source resources for culturally and historically informed research."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ghaboura-etal-2025-time">
<titleInfo>
<title>Time Travel: A Comprehensive Benchmark to Evaluate LMMs on Historical and Cultural Artifacts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Ghaboura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ketan</namePart>
<namePart type="given">Pravin</namePart>
<namePart type="family">More</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Thawkar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wafa</namePart>
<namePart type="given">Al</namePart>
<namePart type="family">Ghallabi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omkar</namePart>
<namePart type="family">Thawakar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fahad</namePart>
<namePart type="given">Shahbaz</namePart>
<namePart type="family">Khan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hisham</namePart>
<namePart type="family">Cholakkal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salman</namePart>
<namePart type="family">Khan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rao</namePart>
<namePart type="given">Muhammad</namePart>
<namePart type="family">Anwer</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>Understanding historical and cultural artifacts demands human expertise and advanced computational techniques, yet the process remains complex and time-intensive. While large multimodal models offer promising support, their evaluation and improvement require a standardized benchmark. To address this, we introduce TimeTravel, a benchmark of 10,250 expert-verified samples spanning 266 distinct cultures across 10 major historical regions. Designed for AI-driven analysis of manuscripts, artworks, inscriptions, and archaeological discoveries, TimeTravel provides a structured dataset and robust evaluation framework to assess AI models’ capabilities in classification, interpretation, and historical comprehension. By integrating AI with historical research, TimeTravel fosters AI-powered tools for historians, archaeologists, researchers, and cultural tourists to extract valuable insights while ensuring technology contributes meaningfully to historical discovery and cultural heritage preservation. We evaluate contemporary AI models on TimeTravel, highlighting their strengths and identifying areas for improvement. Our goal is to establish AI as a reliable partner in preserving cultural heritage, ensuring that technological advancements contribute meaningfully to historical discovery. We release the TimeTravel dataset and evaluation suite as open-source resources for culturally and historically informed research.</abstract>
<identifier type="citekey">ghaboura-etal-2025-time</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.1211</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.1211/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>23627</start>
<end>23641</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Time Travel: A Comprehensive Benchmark to Evaluate LMMs on Historical and Cultural Artifacts
%A Ghaboura, Sara
%A More, Ketan Pravin
%A Thawkar, Ritesh
%A Ghallabi, Wafa Al
%A Thawakar, Omkar
%A Khan, Fahad Shahbaz
%A Cholakkal, Hisham
%A Khan, Salman
%A Anwer, Rao Muhammad
%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 ghaboura-etal-2025-time
%X Understanding historical and cultural artifacts demands human expertise and advanced computational techniques, yet the process remains complex and time-intensive. While large multimodal models offer promising support, their evaluation and improvement require a standardized benchmark. To address this, we introduce TimeTravel, a benchmark of 10,250 expert-verified samples spanning 266 distinct cultures across 10 major historical regions. Designed for AI-driven analysis of manuscripts, artworks, inscriptions, and archaeological discoveries, TimeTravel provides a structured dataset and robust evaluation framework to assess AI models’ capabilities in classification, interpretation, and historical comprehension. By integrating AI with historical research, TimeTravel fosters AI-powered tools for historians, archaeologists, researchers, and cultural tourists to extract valuable insights while ensuring technology contributes meaningfully to historical discovery and cultural heritage preservation. We evaluate contemporary AI models on TimeTravel, highlighting their strengths and identifying areas for improvement. Our goal is to establish AI as a reliable partner in preserving cultural heritage, ensuring that technological advancements contribute meaningfully to historical discovery. We release the TimeTravel dataset and evaluation suite as open-source resources for culturally and historically informed research.
%R 10.18653/v1/2025.findings-acl.1211
%U https://aclanthology.org/2025.findings-acl.1211/
%U https://doi.org/10.18653/v1/2025.findings-acl.1211
%P 23627-23641
Markdown (Informal)
[Time Travel: A Comprehensive Benchmark to Evaluate LMMs on Historical and Cultural Artifacts](https://aclanthology.org/2025.findings-acl.1211/) (Ghaboura et al., Findings 2025)
ACL
- Sara Ghaboura, Ketan Pravin More, Ritesh Thawkar, Wafa Al Ghallabi, Omkar Thawakar, Fahad Shahbaz Khan, Hisham Cholakkal, Salman Khan, and Rao Muhammad Anwer. 2025. Time Travel: A Comprehensive Benchmark to Evaluate LMMs on Historical and Cultural Artifacts. In Findings of the Association for Computational Linguistics: ACL 2025, pages 23627–23641, Vienna, Austria. Association for Computational Linguistics.