<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="miranda-pena-etal-2024-llms">
    <titleInfo>
        <title>Do LLMs Generate Creative and Visually Accessible Data visualisations?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Clarissa</namePart>
        <namePart type="family">Miranda-Pena</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Andrew</namePart>
        <namePart type="family">Reeson</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Cécile</namePart>
        <namePart type="family">Paris</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Josiah</namePart>
        <namePart type="family">Poon</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jonathan</namePart>
        <namePart type="given">K</namePart>
        <namePart type="family">Kummerfeld</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 22nd Annual Workshop of the Australasian Language Technology Association</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Tim</namePart>
            <namePart type="family">Baldwin</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sergio</namePart>
            <namePart type="given">José</namePart>
            <namePart type="family">Rodríguez Méndez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nicholas</namePart>
            <namePart type="family">Kuo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Canberra, Australia</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Data visualisation is a valuable task that combines careful data processing with creative design. Large Language Models (LLMs) are now capable of responding to a data visualisation request in natural language with code that generates accurate data visualisations (e.g., using Matplotlib), but what about human-centered factors, such as the creativity and accessibility of the data visualisations? In this work, we study human perceptions of creativity in the data visualisations generated by LLMs, and propose metrics for accessibility. We generate a range of visualisations using GPT-4 and Claude-2 with controlled variations in prompt and inference parameters, to encourage the generation of different types of data visualisations for the same data. Subsets of these data visualisations are presented to people in a survey with questions that probe human perceptions of different aspects of creativity and accessibility. We find that the models produce visualisations that are novel, but not surprising. Our results also show that our accessibility metrics are consistent with human judgements. In all respects, the LLMs underperform visualisations produced by human-written code. To go beyond the simplest requests, these models need to become aware of human-centered factors, while maintaining accuracy.</abstract>
    <identifier type="citekey">miranda-pena-etal-2024-llms</identifier>
    <location>
        <url>https://aclanthology.org/2024.alta-1.2/</url>
    </location>
    <part>
        <date>2024-12</date>
        <extent unit="page">
            <start>12</start>
            <end>29</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Do LLMs Generate Creative and Visually Accessible Data visualisations?
%A Miranda-Pena, Clarissa
%A Reeson, Andrew
%A Paris, Cécile
%A Poon, Josiah
%A Kummerfeld, Jonathan K.
%Y Baldwin, Tim
%Y Rodríguez Méndez, Sergio José
%Y Kuo, Nicholas
%S Proceedings of the 22nd Annual Workshop of the Australasian Language Technology Association
%D 2024
%8 December
%I Association for Computational Linguistics
%C Canberra, Australia
%F miranda-pena-etal-2024-llms
%X Data visualisation is a valuable task that combines careful data processing with creative design. Large Language Models (LLMs) are now capable of responding to a data visualisation request in natural language with code that generates accurate data visualisations (e.g., using Matplotlib), but what about human-centered factors, such as the creativity and accessibility of the data visualisations? In this work, we study human perceptions of creativity in the data visualisations generated by LLMs, and propose metrics for accessibility. We generate a range of visualisations using GPT-4 and Claude-2 with controlled variations in prompt and inference parameters, to encourage the generation of different types of data visualisations for the same data. Subsets of these data visualisations are presented to people in a survey with questions that probe human perceptions of different aspects of creativity and accessibility. We find that the models produce visualisations that are novel, but not surprising. Our results also show that our accessibility metrics are consistent with human judgements. In all respects, the LLMs underperform visualisations produced by human-written code. To go beyond the simplest requests, these models need to become aware of human-centered factors, while maintaining accuracy.
%U https://aclanthology.org/2024.alta-1.2/
%P 12-29

Markdown (Informal)

[Do LLMs Generate Creative and Visually Accessible Data visualisations?](https://aclanthology.org/2024.alta-1.2/) (Miranda-Pena et al., ALTA 2024)

• Do LLMs Generate Creative and Visually Accessible Data visualisations? (Miranda-Pena et al., ALTA 2024)

ACL

• Clarissa Miranda-Pena, Andrew Reeson, Cécile Paris, Josiah Poon, and Jonathan K. Kummerfeld. 2024. Do LLMs Generate Creative and Visually Accessible Data visualisations?. In Proceedings of the 22nd Annual Workshop of the Australasian Language Technology Association, pages 12–29, Canberra, Australia. Association for Computational Linguistics.