@inproceedings{borisova-etal-2025-table,
title = "Table Understanding and (Multimodal) {LLM}s: A Cross-Domain Case Study on Scientific vs. Non-Scientific Data",
author = {Borisova, Ekaterina and
Barth, Fabio and
Feldhus, Nils and
Abu Ahmad, Raia and
Ostendorff, Malte and
Ortiz Suarez, Pedro and
Rehm, Georg and
M{\"o}ller, Sebastian},
editor = "Chang, Shuaichen and
Hulsebos, Madelon and
Liu, Qian and
Chen, Wenhu and
Sun, Huan",
booktitle = "Proceedings of the 4th Table Representation Learning Workshop",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.trl-1.10/",
doi = "10.18653/v1/2025.trl-1.10",
pages = "109--142",
ISBN = "979-8-89176-268-8",
abstract = "Tables are among the most widely used tools for representing structured data in research, business, medicine, and education. Although LLMs demonstrate strong performance in downstream tasks, their efficiency in processing tabular data remains underexplored. In this paper, we investigate the effectiveness of both text-based and multimodal LLMs on table understanding tasks through a cross-domain and cross-modality evaluation. Specifically, we compare their performance on tables from scientific vs. non-scientific contexts and examine their robustness on tables represented as images vs. text. Additionally, we conduct an interpretability analysis to measure context usage and input relevance. We also introduce the TableEval benchmark, comprising 3017 tables from scholarly publications, Wikipedia, and financial reports, where each table is provided in five different formats: Image, Dictionary, HTML, XML, and LaTeX. Our findings indicate that while LLMs maintain robustness across table modalities, they face significant challenges when processing scientific tables."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="borisova-etal-2025-table">
<titleInfo>
<title>Table Understanding and (Multimodal) LLMs: A Cross-Domain Case Study on Scientific vs. Non-Scientific Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Borisova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabio</namePart>
<namePart type="family">Barth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nils</namePart>
<namePart type="family">Feldhus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raia</namePart>
<namePart type="family">Abu Ahmad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malte</namePart>
<namePart type="family">Ostendorff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pedro</namePart>
<namePart type="family">Ortiz Suarez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Möller</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>Proceedings of the 4th Table Representation Learning Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shuaichen</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Madelon</namePart>
<namePart type="family">Hulsebos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qian</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenhu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huan</namePart>
<namePart type="family">Sun</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">979-8-89176-268-8</identifier>
</relatedItem>
<abstract>Tables are among the most widely used tools for representing structured data in research, business, medicine, and education. Although LLMs demonstrate strong performance in downstream tasks, their efficiency in processing tabular data remains underexplored. In this paper, we investigate the effectiveness of both text-based and multimodal LLMs on table understanding tasks through a cross-domain and cross-modality evaluation. Specifically, we compare their performance on tables from scientific vs. non-scientific contexts and examine their robustness on tables represented as images vs. text. Additionally, we conduct an interpretability analysis to measure context usage and input relevance. We also introduce the TableEval benchmark, comprising 3017 tables from scholarly publications, Wikipedia, and financial reports, where each table is provided in five different formats: Image, Dictionary, HTML, XML, and LaTeX. Our findings indicate that while LLMs maintain robustness across table modalities, they face significant challenges when processing scientific tables.</abstract>
<identifier type="citekey">borisova-etal-2025-table</identifier>
<identifier type="doi">10.18653/v1/2025.trl-1.10</identifier>
<location>
<url>https://aclanthology.org/2025.trl-1.10/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>109</start>
<end>142</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Table Understanding and (Multimodal) LLMs: A Cross-Domain Case Study on Scientific vs. Non-Scientific Data
%A Borisova, Ekaterina
%A Barth, Fabio
%A Feldhus, Nils
%A Abu Ahmad, Raia
%A Ostendorff, Malte
%A Ortiz Suarez, Pedro
%A Rehm, Georg
%A Möller, Sebastian
%Y Chang, Shuaichen
%Y Hulsebos, Madelon
%Y Liu, Qian
%Y Chen, Wenhu
%Y Sun, Huan
%S Proceedings of the 4th Table Representation Learning Workshop
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-268-8
%F borisova-etal-2025-table
%X Tables are among the most widely used tools for representing structured data in research, business, medicine, and education. Although LLMs demonstrate strong performance in downstream tasks, their efficiency in processing tabular data remains underexplored. In this paper, we investigate the effectiveness of both text-based and multimodal LLMs on table understanding tasks through a cross-domain and cross-modality evaluation. Specifically, we compare their performance on tables from scientific vs. non-scientific contexts and examine their robustness on tables represented as images vs. text. Additionally, we conduct an interpretability analysis to measure context usage and input relevance. We also introduce the TableEval benchmark, comprising 3017 tables from scholarly publications, Wikipedia, and financial reports, where each table is provided in five different formats: Image, Dictionary, HTML, XML, and LaTeX. Our findings indicate that while LLMs maintain robustness across table modalities, they face significant challenges when processing scientific tables.
%R 10.18653/v1/2025.trl-1.10
%U https://aclanthology.org/2025.trl-1.10/
%U https://doi.org/10.18653/v1/2025.trl-1.10
%P 109-142
Markdown (Informal)
[Table Understanding and (Multimodal) LLMs: A Cross-Domain Case Study on Scientific vs. Non-Scientific Data](https://aclanthology.org/2025.trl-1.10/) (Borisova et al., TRL 2025)
ACL
- Ekaterina Borisova, Fabio Barth, Nils Feldhus, Raia Abu Ahmad, Malte Ostendorff, Pedro Ortiz Suarez, Georg Rehm, and Sebastian Möller. 2025. Table Understanding and (Multimodal) LLMs: A Cross-Domain Case Study on Scientific vs. Non-Scientific Data. In Proceedings of the 4th Table Representation Learning Workshop, pages 109–142, Vienna, Austria. Association for Computational Linguistics.