@inproceedings{shankarampeta-etal-2025-transienttables,
title = "{TRANSIENTTABLES}: Evaluating {LLM}s' Reasoning on Temporally Evolving Semi-structured Tables",
author = "Shankarampeta, Abhilash and
Mahajan, Harsh and
Kataria, Tushar and
Roth, Dan and
Gupta, Vivek",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-long.332/",
doi = "10.18653/v1/2025.naacl-long.332",
pages = "6526--6544",
ISBN = "979-8-89176-189-6",
abstract = "Humans continuously make new discoveries, and understanding temporal sequence of events leading to these breakthroughs is essential for advancing science and society. This ability to reason over time allows us to identify future steps and understand the effects of financial and political decisions on our lives. However, large language models (LLMs) are typically trained on static datasets, limiting their ability to perform effective temporal reasoning. To assess the temporal reasoning capabilities of LLMs, we present the TRANSIENTTABLES dataset, which comprises 3,971 questions derived from over 14,000 tables, spanning 1,238 entities across multiple time periods. We introduce a template-based question-generation pipeline that harnesses LLMs to refine both templates and questions. Additionally, we establish baseline results using state-of-the-art LLMs to create a benchmark. We also introduce novel modeling strategies centered around task decomposition, enhancing LLM performance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shankarampeta-etal-2025-transienttables">
<titleInfo>
<title>TRANSIENTTABLES: Evaluating LLMs’ Reasoning on Temporally Evolving Semi-structured Tables</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abhilash</namePart>
<namePart type="family">Shankarampeta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harsh</namePart>
<namePart type="family">Mahajan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tushar</namePart>
<namePart type="family">Kataria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Roth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-189-6</identifier>
</relatedItem>
<abstract>Humans continuously make new discoveries, and understanding temporal sequence of events leading to these breakthroughs is essential for advancing science and society. This ability to reason over time allows us to identify future steps and understand the effects of financial and political decisions on our lives. However, large language models (LLMs) are typically trained on static datasets, limiting their ability to perform effective temporal reasoning. To assess the temporal reasoning capabilities of LLMs, we present the TRANSIENTTABLES dataset, which comprises 3,971 questions derived from over 14,000 tables, spanning 1,238 entities across multiple time periods. We introduce a template-based question-generation pipeline that harnesses LLMs to refine both templates and questions. Additionally, we establish baseline results using state-of-the-art LLMs to create a benchmark. We also introduce novel modeling strategies centered around task decomposition, enhancing LLM performance.</abstract>
<identifier type="citekey">shankarampeta-etal-2025-transienttables</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-long.332</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-long.332/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>6526</start>
<end>6544</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TRANSIENTTABLES: Evaluating LLMs’ Reasoning on Temporally Evolving Semi-structured Tables
%A Shankarampeta, Abhilash
%A Mahajan, Harsh
%A Kataria, Tushar
%A Roth, Dan
%A Gupta, Vivek
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F shankarampeta-etal-2025-transienttables
%X Humans continuously make new discoveries, and understanding temporal sequence of events leading to these breakthroughs is essential for advancing science and society. This ability to reason over time allows us to identify future steps and understand the effects of financial and political decisions on our lives. However, large language models (LLMs) are typically trained on static datasets, limiting their ability to perform effective temporal reasoning. To assess the temporal reasoning capabilities of LLMs, we present the TRANSIENTTABLES dataset, which comprises 3,971 questions derived from over 14,000 tables, spanning 1,238 entities across multiple time periods. We introduce a template-based question-generation pipeline that harnesses LLMs to refine both templates and questions. Additionally, we establish baseline results using state-of-the-art LLMs to create a benchmark. We also introduce novel modeling strategies centered around task decomposition, enhancing LLM performance.
%R 10.18653/v1/2025.naacl-long.332
%U https://aclanthology.org/2025.naacl-long.332/
%U https://doi.org/10.18653/v1/2025.naacl-long.332
%P 6526-6544
Markdown (Informal)
[TRANSIENTTABLES: Evaluating LLMs’ Reasoning on Temporally Evolving Semi-structured Tables](https://aclanthology.org/2025.naacl-long.332/) (Shankarampeta et al., NAACL 2025)
ACL