<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2023-elaboration">
    <titleInfo>
        <title>Elaboration-Generating Commonsense Question Answering at Scale</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Wenya</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Vivek</namePart>
        <namePart type="family">Srikumar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hannaneh</namePart>
        <namePart type="family">Hajishirzi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Noah</namePart>
        <namePart type="given">A</namePart>
        <namePart type="family">Smith</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 1: Long 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>In question answering requiring common sense, language models (e.g., GPT-3) have been used to generate text expressing background knowledge that helps improve performance. Yet the cost of working with such models is very high; in this work, we finetune smaller language models to generate useful intermediate context, referred to here as elaborations. Our framework alternates between updating two language models—an elaboration generator and an answer predictor—allowing each to influence the other. Using less than 0.5% of the parameters of GPT-3, our model outperforms alternatives with similar sizes and closes the gap with GPT-3 on four commonsense question answering benchmarks. Human evaluations show that the quality of the generated elaborations is high.</abstract>
    <identifier type="citekey">wang-etal-2023-elaboration</identifier>
    <identifier type="doi">10.18653/v1/2023.acl-long.90</identifier>
    <location>
        <url>https://aclanthology.org/2023.acl-long.90</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>1619</start>
            <end>1635</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Elaboration-Generating Commonsense Question Answering at Scale
%A Wang, Wenya
%A Srikumar, Vivek
%A Hajishirzi, Hannaneh
%A Smith, Noah A.
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F wang-etal-2023-elaboration
%X In question answering requiring common sense, language models (e.g., GPT-3) have been used to generate text expressing background knowledge that helps improve performance. Yet the cost of working with such models is very high; in this work, we finetune smaller language models to generate useful intermediate context, referred to here as elaborations. Our framework alternates between updating two language models—an elaboration generator and an answer predictor—allowing each to influence the other. Using less than 0.5% of the parameters of GPT-3, our model outperforms alternatives with similar sizes and closes the gap with GPT-3 on four commonsense question answering benchmarks. Human evaluations show that the quality of the generated elaborations is high.
%R 10.18653/v1/2023.acl-long.90
%U https://aclanthology.org/2023.acl-long.90
%U https://doi.org/10.18653/v1/2023.acl-long.90
%P 1619-1635

Markdown (Informal)

[Elaboration-Generating Commonsense Question Answering at Scale](https://aclanthology.org/2023.acl-long.90) (Wang et al., ACL 2023)

• Elaboration-Generating Commonsense Question Answering at Scale (Wang et al., ACL 2023)

ACL

• Wenya Wang, Vivek Srikumar, Hannaneh Hajishirzi, and Noah A. Smith. 2023. Elaboration-Generating Commonsense Question Answering at Scale. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1619–1635, Toronto, Canada. Association for Computational Linguistics.