@inproceedings{akhtar-etal-2023-exploring,
title = "Exploring the Numerical Reasoning Capabilities of Language Models: A Comprehensive Analysis on Tabular Data",
author = "Akhtar, Mubashara and
Shankarampeta, Abhilash and
Gupta, Vivek and
Patil, Arpit and
Cocarascu, Oana and
Simperl, Elena",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.1028",
doi = "10.18653/v1/2023.findings-emnlp.1028",
pages = "15391--15405",
abstract = "Numerical data plays a crucial role in various real-world domains like finance, economics, and science. Thus, understanding and reasoning with numbers are essential in these fields. Recent benchmarks have assessed the numerical reasoning abilities of language models, revealing their limitations in limited and specific numerical aspects. In this paper, we propose a complete hierarchical taxonomy for numerical reasoning skills, encompassing over ten reasoning types across four levels: representation, number sense, manipulation, and complex reasoning. We conduct a comprehensive evaluation of state-of-the-art models on all reasoning types. To identify challenging reasoning types for different model types, we develop a diverse and extensive set of numerical probes and measure performance shifts. By employing a semi-automated approach, we focus on the tabular Natural Language Inference (TNLI) task as a case study. While no single model excels in all reasoning types, FlanT5 (few-/zero-shot) and GPT3.5 (few-shot) demonstrate strong overall numerical reasoning skills compared to other models in our probes.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="akhtar-etal-2023-exploring">
<titleInfo>
<title>Exploring the Numerical Reasoning Capabilities of Language Models: A Comprehensive Analysis on Tabular Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mubashara</namePart>
<namePart type="family">Akhtar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhilash</namePart>
<namePart type="family">Shankarampeta</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>
<name type="personal">
<namePart type="given">Arpit</namePart>
<namePart type="family">Patil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oana</namePart>
<namePart type="family">Cocarascu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Simperl</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>Findings of the Association for Computational Linguistics: EMNLP 2023</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>Numerical data plays a crucial role in various real-world domains like finance, economics, and science. Thus, understanding and reasoning with numbers are essential in these fields. Recent benchmarks have assessed the numerical reasoning abilities of language models, revealing their limitations in limited and specific numerical aspects. In this paper, we propose a complete hierarchical taxonomy for numerical reasoning skills, encompassing over ten reasoning types across four levels: representation, number sense, manipulation, and complex reasoning. We conduct a comprehensive evaluation of state-of-the-art models on all reasoning types. To identify challenging reasoning types for different model types, we develop a diverse and extensive set of numerical probes and measure performance shifts. By employing a semi-automated approach, we focus on the tabular Natural Language Inference (TNLI) task as a case study. While no single model excels in all reasoning types, FlanT5 (few-/zero-shot) and GPT3.5 (few-shot) demonstrate strong overall numerical reasoning skills compared to other models in our probes.</abstract>
<identifier type="citekey">akhtar-etal-2023-exploring</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.1028</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.1028</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>15391</start>
<end>15405</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring the Numerical Reasoning Capabilities of Language Models: A Comprehensive Analysis on Tabular Data
%A Akhtar, Mubashara
%A Shankarampeta, Abhilash
%A Gupta, Vivek
%A Patil, Arpit
%A Cocarascu, Oana
%A Simperl, Elena
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F akhtar-etal-2023-exploring
%X Numerical data plays a crucial role in various real-world domains like finance, economics, and science. Thus, understanding and reasoning with numbers are essential in these fields. Recent benchmarks have assessed the numerical reasoning abilities of language models, revealing their limitations in limited and specific numerical aspects. In this paper, we propose a complete hierarchical taxonomy for numerical reasoning skills, encompassing over ten reasoning types across four levels: representation, number sense, manipulation, and complex reasoning. We conduct a comprehensive evaluation of state-of-the-art models on all reasoning types. To identify challenging reasoning types for different model types, we develop a diverse and extensive set of numerical probes and measure performance shifts. By employing a semi-automated approach, we focus on the tabular Natural Language Inference (TNLI) task as a case study. While no single model excels in all reasoning types, FlanT5 (few-/zero-shot) and GPT3.5 (few-shot) demonstrate strong overall numerical reasoning skills compared to other models in our probes.
%R 10.18653/v1/2023.findings-emnlp.1028
%U https://aclanthology.org/2023.findings-emnlp.1028
%U https://doi.org/10.18653/v1/2023.findings-emnlp.1028
%P 15391-15405
Markdown (Informal)
[Exploring the Numerical Reasoning Capabilities of Language Models: A Comprehensive Analysis on Tabular Data](https://aclanthology.org/2023.findings-emnlp.1028) (Akhtar et al., Findings 2023)
ACL