<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="park-etal-2024-coconut">
    <titleInfo>
        <title>Coconut: Contextualized Commonsense Unified Transformers for Graph-Based Commonsense Augmentation of Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jun-Hyung</namePart>
        <namePart type="family">Park</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mingyu</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Junho</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">SangKeun</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics ACL 2024</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Lun-Wei</namePart>
            <namePart type="family">Ku</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Andre</namePart>
            <namePart type="family">Martins</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Vivek</namePart>
            <namePart type="family">Srikumar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Bangkok, Thailand and virtual meeting</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In this paper, we introduce COCONUT to effectively guide the contextualization of structured commonsense knowledge based on largelanguage models. COCONUT employs a contextualized knowledge prompting scheme to gather high-quality contextualization examplesfrom a large language model. These examples are subsequently distilled into small language models to enhance their contextualization capability. Extensive evaluations show that COCONUT considerably improves commonsense reasoning performance across diverse benchmarks, models, and settings, exhibiting its flexibility and universality in generating contextualized commonsense knowledge. Notably,COCONUT consistently outperforms the state-of-the-art technique by an average of 5.8%.</abstract>
    <identifier type="citekey">park-etal-2024-coconut</identifier>
    <location>
        <url>https://aclanthology.org/2024.findings-acl.346</url>
    </location>
    <part>
        <date>2024-08</date>
        <extent unit="page">
            <start>5815</start>
            <end>5830</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Coconut: Contextualized Commonsense Unified Transformers for Graph-Based Commonsense Augmentation of Language Models
%A Park, Jun-Hyung
%A Lee, Mingyu
%A Kim, Junho
%A Lee, SangKeun
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F park-etal-2024-coconut
%X In this paper, we introduce COCONUT to effectively guide the contextualization of structured commonsense knowledge based on largelanguage models. COCONUT employs a contextualized knowledge prompting scheme to gather high-quality contextualization examplesfrom a large language model. These examples are subsequently distilled into small language models to enhance their contextualization capability. Extensive evaluations show that COCONUT considerably improves commonsense reasoning performance across diverse benchmarks, models, and settings, exhibiting its flexibility and universality in generating contextualized commonsense knowledge. Notably,COCONUT consistently outperforms the state-of-the-art technique by an average of 5.8%.
%U https://aclanthology.org/2024.findings-acl.346
%P 5815-5830

Markdown (Informal)

[Coconut: Contextualized Commonsense Unified Transformers for Graph-Based Commonsense Augmentation of Language Models](https://aclanthology.org/2024.findings-acl.346) (Park et al., Findings 2024)

• Coconut: Contextualized Commonsense Unified Transformers for Graph-Based Commonsense Augmentation of Language Models (Park et al., Findings 2024)

ACL

• Jun-Hyung Park, Mingyu Lee, Junho Kim, and SangKeun Lee. 2024. Coconut: Contextualized Commonsense Unified Transformers for Graph-Based Commonsense Augmentation of Language Models. In Findings of the Association for Computational Linguistics ACL 2024, pages 5815–5830, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.