<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-lu-2023-learning">
    <titleInfo>
        <title>Learning Multi-Step Reasoning by Solving Arithmetic Tasks</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tianduo</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wei</namePart>
        <namePart type="family">Lu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Rogers</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jordan</namePart>
            <namePart type="family">Boyd-Graber</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Naoaki</namePart>
            <namePart type="family">Okazaki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Toronto, Canada</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Mathematical reasoning is regarded as a necessary ability for Language Models (LMs). Recent works demonstrate large LMs’ impressive performance in solving math problems. The success is attributed to their Chain-of-Thought (CoT) reasoning abilities, i.e., the ability to decompose complex questions into step-by-step reasoning chains, but such ability seems only to emerge from models with abundant parameters. This work investigates how to incorporate relatively small LMs with the capabilities of multi-step reasoning. We propose to inject such abilities by continually pre-training LMs on a synthetic dataset MsAT which is composed of Multi-step Arithmetic Tasks. Our experiments on four math word problem datasets show the effectiveness of the proposed method in enhancing LMs’ math reasoning abilities.</abstract>
    <identifier type="citekey">wang-lu-2023-learning</identifier>
    <identifier type="doi">10.18653/v1/2023.acl-short.106</identifier>
    <location>
        <url>https://aclanthology.org/2023.acl-short.106</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>1229</start>
            <end>1238</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Learning Multi-Step Reasoning by Solving Arithmetic Tasks
%A Wang, Tianduo
%A Lu, Wei
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F wang-lu-2023-learning
%X Mathematical reasoning is regarded as a necessary ability for Language Models (LMs). Recent works demonstrate large LMs’ impressive performance in solving math problems. The success is attributed to their Chain-of-Thought (CoT) reasoning abilities, i.e., the ability to decompose complex questions into step-by-step reasoning chains, but such ability seems only to emerge from models with abundant parameters. This work investigates how to incorporate relatively small LMs with the capabilities of multi-step reasoning. We propose to inject such abilities by continually pre-training LMs on a synthetic dataset MsAT which is composed of Multi-step Arithmetic Tasks. Our experiments on four math word problem datasets show the effectiveness of the proposed method in enhancing LMs’ math reasoning abilities.
%R 10.18653/v1/2023.acl-short.106
%U https://aclanthology.org/2023.acl-short.106
%U https://doi.org/10.18653/v1/2023.acl-short.106
%P 1229-1238

Markdown (Informal)

[Learning Multi-Step Reasoning by Solving Arithmetic Tasks](https://aclanthology.org/2023.acl-short.106) (Wang & Lu, ACL 2023)

• Learning Multi-Step Reasoning by Solving Arithmetic Tasks (Wang & Lu, ACL 2023)

ACL

• Tianduo Wang and Wei Lu. 2023. Learning Multi-Step Reasoning by Solving Arithmetic Tasks. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 1229–1238, Toronto, Canada. Association for Computational Linguistics.