<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ding-etal-2023-harnessing">
    <titleInfo>
        <title>Harnessing the power of LLMs: Evaluating human-AI text co-creation through the lens of news headline generation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zijian</namePart>
        <namePart type="family">Ding</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alison</namePart>
        <namePart type="family">Smith-Renner</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wenjuan</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Joel</namePart>
        <namePart type="family">Tetreault</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alejandro</namePart>
        <namePart type="family">Jaimes</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>To explore how humans can best leverage LLMs for writing and how interacting with these models affects feelings of ownership and trust in the writing process, we compared common human-AI interaction types (e.g., guiding system, selecting from system outputs, post-editing outputs) in the context of LLM-assisted news headline generation. While LLMs alone can generate satisfactory news headlines, on average, human control is needed to fix undesirable model outputs. Of the interaction methods, guiding and selecting model output added the most benefit with the lowest cost (in time and effort). Further, AI assistance did not harm participants’ perception of control compared to freeform editing.</abstract>
    <identifier type="citekey">ding-etal-2023-harnessing</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-emnlp.217</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-emnlp.217</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>3321</start>
            <end>3339</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Harnessing the power of LLMs: Evaluating human-AI text co-creation through the lens of news headline generation
%A Ding, Zijian
%A Smith-Renner, Alison
%A Zhang, Wenjuan
%A Tetreault, Joel
%A Jaimes, Alejandro
%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 ding-etal-2023-harnessing
%X To explore how humans can best leverage LLMs for writing and how interacting with these models affects feelings of ownership and trust in the writing process, we compared common human-AI interaction types (e.g., guiding system, selecting from system outputs, post-editing outputs) in the context of LLM-assisted news headline generation. While LLMs alone can generate satisfactory news headlines, on average, human control is needed to fix undesirable model outputs. Of the interaction methods, guiding and selecting model output added the most benefit with the lowest cost (in time and effort). Further, AI assistance did not harm participants’ perception of control compared to freeform editing.
%R 10.18653/v1/2023.findings-emnlp.217
%U https://aclanthology.org/2023.findings-emnlp.217
%U https://doi.org/10.18653/v1/2023.findings-emnlp.217
%P 3321-3339

Markdown (Informal)

[Harnessing the power of LLMs: Evaluating human-AI text co-creation through the lens of news headline generation](https://aclanthology.org/2023.findings-emnlp.217) (Ding et al., Findings 2023)

• Harnessing the power of LLMs: Evaluating human-AI text co-creation through the lens of news headline generation (Ding et al., Findings 2023)

ACL

• Zijian Ding, Alison Smith-Renner, Wenjuan Zhang, Joel Tetreault, and Alejandro Jaimes. 2023. Harnessing the power of LLMs: Evaluating human-AI text co-creation through the lens of news headline generation. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 3321–3339, Singapore. Association for Computational Linguistics.