@inproceedings{oses-grijalba-etal-2026-enhancing,
title = "Enhancing and Evaluating Tabular Models on the Fly via Synthetic Question{--}Answer Generation",
author = "Os{\'e}s Grijalba, Jorge and
Mart{\'i}nez C{\'a}mara, Eugenio and
Ure{\~n}-L{\'o}pez, L. Alfonso and
Camacho-Collados, Jose",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.421/",
doi = "10.63317/27e3cist39z2",
pages = "5389--5413",
abstract = "Question Answering (QA) over Tabular Data has been traditionally a challenging task, but LLMs have recently shown the ability to respond to questions related to this type of structured data. However, current tabular QA datasets are skewed toward Wikipedia tables and SQL-style answers composed of human-crafted question{--}answer pairs. This limits the evaluation of LLMs on this task to a narrow genre of data and language, while also requiring extensive human effort for dataset or benchmark creation. To address this, we introduce SynTabQA, a methodology for the automatic generation of synthetic question{--}answer pairs from any unannotated table. SynTabQA defines a detailed question typology, enabling fine-grained evaluation and facilitating the creation of diverse QA datasets. Our approach not only provides an automated test bed for any tabular dataset but can also be used in few-shot settings to supply LLMs with tailored examples, improving their focus and accuracy. We validate SynTabQA on two large, manually constructed tabular QA benchmarks of distinct nature."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="oses-grijalba-etal-2026-enhancing">
<titleInfo>
<title>Enhancing and Evaluating Tabular Models on the Fly via Synthetic Question–Answer Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jorge</namePart>
<namePart type="family">Osés Grijalba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eugenio</namePart>
<namePart type="family">Martínez Cámara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">L</namePart>
<namePart type="given">Alfonso</namePart>
<namePart type="family">Ureñ-López</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jose</namePart>
<namePart type="family">Camacho-Collados</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Question Answering (QA) over Tabular Data has been traditionally a challenging task, but LLMs have recently shown the ability to respond to questions related to this type of structured data. However, current tabular QA datasets are skewed toward Wikipedia tables and SQL-style answers composed of human-crafted question–answer pairs. This limits the evaluation of LLMs on this task to a narrow genre of data and language, while also requiring extensive human effort for dataset or benchmark creation. To address this, we introduce SynTabQA, a methodology for the automatic generation of synthetic question–answer pairs from any unannotated table. SynTabQA defines a detailed question typology, enabling fine-grained evaluation and facilitating the creation of diverse QA datasets. Our approach not only provides an automated test bed for any tabular dataset but can also be used in few-shot settings to supply LLMs with tailored examples, improving their focus and accuracy. We validate SynTabQA on two large, manually constructed tabular QA benchmarks of distinct nature.</abstract>
<identifier type="citekey">oses-grijalba-etal-2026-enhancing</identifier>
<identifier type="doi">10.63317/27e3cist39z2</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.421/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>5389</start>
<end>5413</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing and Evaluating Tabular Models on the Fly via Synthetic Question–Answer Generation
%A Osés Grijalba, Jorge
%A Martínez Cámara, Eugenio
%A Ureñ-López, L. Alfonso
%A Camacho-Collados, Jose
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F oses-grijalba-etal-2026-enhancing
%X Question Answering (QA) over Tabular Data has been traditionally a challenging task, but LLMs have recently shown the ability to respond to questions related to this type of structured data. However, current tabular QA datasets are skewed toward Wikipedia tables and SQL-style answers composed of human-crafted question–answer pairs. This limits the evaluation of LLMs on this task to a narrow genre of data and language, while also requiring extensive human effort for dataset or benchmark creation. To address this, we introduce SynTabQA, a methodology for the automatic generation of synthetic question–answer pairs from any unannotated table. SynTabQA defines a detailed question typology, enabling fine-grained evaluation and facilitating the creation of diverse QA datasets. Our approach not only provides an automated test bed for any tabular dataset but can also be used in few-shot settings to supply LLMs with tailored examples, improving their focus and accuracy. We validate SynTabQA on two large, manually constructed tabular QA benchmarks of distinct nature.
%R 10.63317/27e3cist39z2
%U https://aclanthology.org/2026.lrec-1.421/
%U https://doi.org/10.63317/27e3cist39z2
%P 5389-5413
Markdown (Informal)
[Enhancing and Evaluating Tabular Models on the Fly via Synthetic Question–Answer Generation](https://aclanthology.org/2026.lrec-1.421/) (Osés Grijalba et al., LREC 2026)
ACL