@inproceedings{pancholi-etal-2025-tabxeval,
title = "{T}ab{XE}val: Why this is a Bad Table? An e{X}haustive Rubric for Table Evaluation",
author = "Pancholi, Vihang and
Bafna, Jainit Sushil and
Anvekar, Tejas and
Shrivastava, Manish and
Gupta, Vivek",
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.1176/",
doi = "10.18653/v1/2025.findings-acl.1176",
pages = "22913--22934",
ISBN = "979-8-89176-256-5",
abstract = "Evaluating tables qualitatively and quantitatively poses a significant challenge, as standard metrics often overlook subtle structural and content-level discrepancies. To address this, we propose a rubric-based evaluation framework that integrates multi-level structural descriptors with fine-grained contextual signals, enabling more precise and consistent table comparison. Building on this, we introduce TabXEval, an eXhaustive and eXplainable two-phase evaluation framework. TabXEval first aligns reference and predicted tables structurally via TabAlign, then performs semantic and syntactic comparison using TabCompare, offering interpretable and granular feedback. We evaluate TabXEval on TabXBench, a diverse, multi-domain benchmark featuring realistic table perturbations and human annotations. A sensitivity-specificity analysis further demonstrates the robustness and explainability of TabXEval across varied table tasks. Code and data are available at https://corallab- asu.github.io/tabxeval/."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pancholi-etal-2025-tabxeval">
<titleInfo>
<title>TabXEval: Why this is a Bad Table? An eXhaustive Rubric for Table Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vihang</namePart>
<namePart type="family">Pancholi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jainit</namePart>
<namePart type="given">Sushil</namePart>
<namePart type="family">Bafna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tejas</namePart>
<namePart type="family">Anvekar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manish</namePart>
<namePart type="family">Shrivastava</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>2025-07</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>Evaluating tables qualitatively and quantitatively poses a significant challenge, as standard metrics often overlook subtle structural and content-level discrepancies. To address this, we propose a rubric-based evaluation framework that integrates multi-level structural descriptors with fine-grained contextual signals, enabling more precise and consistent table comparison. Building on this, we introduce TabXEval, an eXhaustive and eXplainable two-phase evaluation framework. TabXEval first aligns reference and predicted tables structurally via TabAlign, then performs semantic and syntactic comparison using TabCompare, offering interpretable and granular feedback. We evaluate TabXEval on TabXBench, a diverse, multi-domain benchmark featuring realistic table perturbations and human annotations. A sensitivity-specificity analysis further demonstrates the robustness and explainability of TabXEval across varied table tasks. Code and data are available at https://corallab- asu.github.io/tabxeval/.</abstract>
<identifier type="citekey">pancholi-etal-2025-tabxeval</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.1176</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.1176/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>22913</start>
<end>22934</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TabXEval: Why this is a Bad Table? An eXhaustive Rubric for Table Evaluation
%A Pancholi, Vihang
%A Bafna, Jainit Sushil
%A Anvekar, Tejas
%A Shrivastava, Manish
%A Gupta, Vivek
%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 pancholi-etal-2025-tabxeval
%X Evaluating tables qualitatively and quantitatively poses a significant challenge, as standard metrics often overlook subtle structural and content-level discrepancies. To address this, we propose a rubric-based evaluation framework that integrates multi-level structural descriptors with fine-grained contextual signals, enabling more precise and consistent table comparison. Building on this, we introduce TabXEval, an eXhaustive and eXplainable two-phase evaluation framework. TabXEval first aligns reference and predicted tables structurally via TabAlign, then performs semantic and syntactic comparison using TabCompare, offering interpretable and granular feedback. We evaluate TabXEval on TabXBench, a diverse, multi-domain benchmark featuring realistic table perturbations and human annotations. A sensitivity-specificity analysis further demonstrates the robustness and explainability of TabXEval across varied table tasks. Code and data are available at https://corallab- asu.github.io/tabxeval/.
%R 10.18653/v1/2025.findings-acl.1176
%U https://aclanthology.org/2025.findings-acl.1176/
%U https://doi.org/10.18653/v1/2025.findings-acl.1176
%P 22913-22934
Markdown (Informal)
[TabXEval: Why this is a Bad Table? An eXhaustive Rubric for Table Evaluation](https://aclanthology.org/2025.findings-acl.1176/) (Pancholi et al., Findings 2025)
ACL