@inproceedings{oses-grijalba-etal-2024-question,
title = "Question Answering over Tabular Data with {D}ata{B}ench: A Large-Scale Empirical Evaluation of {LLM}s",
author = "Os{\'e}s Grijalba, Jorge and
Ure{\~n}a-L{\'o}pez, L. Alfonso and
Mart{\'i}nez C{\'a}mara, Eugenio and
Camacho-Collados, Jose",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1179/",
pages = "13471--13488",
abstract = "Large Language Models (LLMs) are showing emerging abilities, and one of the latest recognized ones deals with their ability to reason and answer questions from tabular data. Although there are some available datasets to assess question answering systems on tabular data, they are not large and diverse enough to properly assess the capabilities of LLMs. To this end, we propose DataBench, a benchmark composed of 65 real-world datasets over several domains, including 20 human-generated questions per dataset, totaling 1300 questions and answers overall. Using this benchmark, we perform a large-scale empirical comparison of several open and closed source models, including both code-generating and in-context learning models. The results highlight the current gap between open-source and closed-source models, with all types of model having room for improvement even in simple boolean questions or involving a single column."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="oses-grijalba-etal-2024-question">
<titleInfo>
<title>Question Answering over Tabular Data with DataBench: A Large-Scale Empirical Evaluation of LLMs</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">L</namePart>
<namePart type="given">Alfonso</namePart>
<namePart type="family">Ureña-López</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">Jose</namePart>
<namePart type="family">Camacho-Collados</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large Language Models (LLMs) are showing emerging abilities, and one of the latest recognized ones deals with their ability to reason and answer questions from tabular data. Although there are some available datasets to assess question answering systems on tabular data, they are not large and diverse enough to properly assess the capabilities of LLMs. To this end, we propose DataBench, a benchmark composed of 65 real-world datasets over several domains, including 20 human-generated questions per dataset, totaling 1300 questions and answers overall. Using this benchmark, we perform a large-scale empirical comparison of several open and closed source models, including both code-generating and in-context learning models. The results highlight the current gap between open-source and closed-source models, with all types of model having room for improvement even in simple boolean questions or involving a single column.</abstract>
<identifier type="citekey">oses-grijalba-etal-2024-question</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1179/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>13471</start>
<end>13488</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Question Answering over Tabular Data with DataBench: A Large-Scale Empirical Evaluation of LLMs
%A Osés Grijalba, Jorge
%A Ureña-López, L. Alfonso
%A Martínez Cámara, Eugenio
%A Camacho-Collados, Jose
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F oses-grijalba-etal-2024-question
%X Large Language Models (LLMs) are showing emerging abilities, and one of the latest recognized ones deals with their ability to reason and answer questions from tabular data. Although there are some available datasets to assess question answering systems on tabular data, they are not large and diverse enough to properly assess the capabilities of LLMs. To this end, we propose DataBench, a benchmark composed of 65 real-world datasets over several domains, including 20 human-generated questions per dataset, totaling 1300 questions and answers overall. Using this benchmark, we perform a large-scale empirical comparison of several open and closed source models, including both code-generating and in-context learning models. The results highlight the current gap between open-source and closed-source models, with all types of model having room for improvement even in simple boolean questions or involving a single column.
%U https://aclanthology.org/2024.lrec-main.1179/
%P 13471-13488
Markdown (Informal)
[Question Answering over Tabular Data with DataBench: A Large-Scale Empirical Evaluation of LLMs](https://aclanthology.org/2024.lrec-main.1179/) (Osés Grijalba et al., LREC-COLING 2024)
ACL