@inproceedings{zhang-etal-2023-crt,
title = "{CRT}-{QA}: A Dataset of Complex Reasoning Question Answering over Tabular Data",
author = "Zhang, Zhehao and
Li, Xitao and
Gao, Yan and
Lou, Jian-Guang",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.132",
doi = "10.18653/v1/2023.emnlp-main.132",
pages = "2131--2153",
abstract = "Large language models (LLMs) show powerful reasoning abilities on various text-based tasks. However, their reasoning capability on structured data such as tables has not been systematically explored. In this work, we first establish a comprehensive taxonomy of reasoning and operation types for tabular data analysis. Then, we construct a complex reasoning QA dataset over tabular data, named CRT-QA dataset (Complex Reasoning QA over Tabular data), with the following unique features: (1) it is the first Table QA dataset with multi-step operation and informal reasoning; (2) it contains fine-grained annotations on questions{'} directness, composition types of sub-questions, and human reasoning paths which can be used to conduct a thorough investigation on LLMs{'} reasoning ability; (3) it contains a collection of unanswerable and indeterminate questions that commonly arise in real-world situations. We further introduce an efficient and effective tool-augmented method, named ARC (Auto-exemplar-guided Reasoning with Code), to use external tools such as Pandas to solve table reasoning tasks without handcrafted demonstrations. The experiment results show that CRT-QA presents a strong challenge for baseline methods and ARC achieves the best result.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2023-crt">
<titleInfo>
<title>CRT-QA: A Dataset of Complex Reasoning Question Answering over Tabular Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhehao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xitao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian-Guang</namePart>
<namePart type="family">Lou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large language models (LLMs) show powerful reasoning abilities on various text-based tasks. However, their reasoning capability on structured data such as tables has not been systematically explored. In this work, we first establish a comprehensive taxonomy of reasoning and operation types for tabular data analysis. Then, we construct a complex reasoning QA dataset over tabular data, named CRT-QA dataset (Complex Reasoning QA over Tabular data), with the following unique features: (1) it is the first Table QA dataset with multi-step operation and informal reasoning; (2) it contains fine-grained annotations on questions’ directness, composition types of sub-questions, and human reasoning paths which can be used to conduct a thorough investigation on LLMs’ reasoning ability; (3) it contains a collection of unanswerable and indeterminate questions that commonly arise in real-world situations. We further introduce an efficient and effective tool-augmented method, named ARC (Auto-exemplar-guided Reasoning with Code), to use external tools such as Pandas to solve table reasoning tasks without handcrafted demonstrations. The experiment results show that CRT-QA presents a strong challenge for baseline methods and ARC achieves the best result.</abstract>
<identifier type="citekey">zhang-etal-2023-crt</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.132</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.132</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>2131</start>
<end>2153</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CRT-QA: A Dataset of Complex Reasoning Question Answering over Tabular Data
%A Zhang, Zhehao
%A Li, Xitao
%A Gao, Yan
%A Lou, Jian-Guang
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F zhang-etal-2023-crt
%X Large language models (LLMs) show powerful reasoning abilities on various text-based tasks. However, their reasoning capability on structured data such as tables has not been systematically explored. In this work, we first establish a comprehensive taxonomy of reasoning and operation types for tabular data analysis. Then, we construct a complex reasoning QA dataset over tabular data, named CRT-QA dataset (Complex Reasoning QA over Tabular data), with the following unique features: (1) it is the first Table QA dataset with multi-step operation and informal reasoning; (2) it contains fine-grained annotations on questions’ directness, composition types of sub-questions, and human reasoning paths which can be used to conduct a thorough investigation on LLMs’ reasoning ability; (3) it contains a collection of unanswerable and indeterminate questions that commonly arise in real-world situations. We further introduce an efficient and effective tool-augmented method, named ARC (Auto-exemplar-guided Reasoning with Code), to use external tools such as Pandas to solve table reasoning tasks without handcrafted demonstrations. The experiment results show that CRT-QA presents a strong challenge for baseline methods and ARC achieves the best result.
%R 10.18653/v1/2023.emnlp-main.132
%U https://aclanthology.org/2023.emnlp-main.132
%U https://doi.org/10.18653/v1/2023.emnlp-main.132
%P 2131-2153
Markdown (Informal)
[CRT-QA: A Dataset of Complex Reasoning Question Answering over Tabular Data](https://aclanthology.org/2023.emnlp-main.132) (Zhang et al., EMNLP 2023)
ACL