VectorEdits: A Dataset and Benchmark for Instruction-Based Editing of Vector Graphics

Josef Kuchar; Marek Kadlčík; Michal Spiegel; Michal Štefánik

doi:10.63317/5gc5ibtb5k8i

VectorEdits: A Dataset and Benchmark for Instruction-Based Editing of Vector Graphics

Josef Kuchar, Marek Kadlcik, Michal Spiegel, Michal Stefanik

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use ... for bold, ... for italic, ... for underline, <sc>...</sc> for small-caps, <tt>...<tt> for typewriter text, <url>...</url> for URLs, <a href=...> for hyperlinks, and <par/> for paragraph breaks.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the external publication .)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

We introduce a large-scale dataset for instruction-guided vector image editing, consisting of over 270,000 pairs of SVG images paired with natural language edit instructions. Our dataset enables training and evaluation of models that modify vector graphics based on textual commands. We describe the data collection process, including image pairing via CLIP similarity and instruction generation with vision-language models. Initial experiments with state-of-the-art large language models reveal that current methods struggle to produce accurate and valid edits, underscoring the challenge of this task. To foster research in natural language-driven vector graphic generation and editing, we make our resources created within this work publicly available.

Anthology ID:: 2026.lrec-1.868
Volume:: Proceedings of the Fifteenth Language Resources and Evaluation Conference
Month:: May
Year:: 2026
Address:: Palma de Mallorca, Spain
Editors:: Stelios Piperidis, Núria Bel, Henk van den Heuvel, Nancy Ide, Simon Krek, Antonio Toral
Venue:: LREC
SIG:
Publisher:: ELRA Language Resource Association
Note:
Pages:: 11119–11124
Language:
External URL:: https://lrec.elra.info/lrec2026-main-868
DOI:: 10.63317/5gc5ibtb5k8i
Bibkey:
Cite (ACL):: Josef Kuchar, Marek Kadlcik, Michal Spiegel, and Michal Stefanik. 2026. VectorEdits: A Dataset and Benchmark for Instruction-Based Editing of Vector Graphics. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 11119–11124, Palma de Mallorca, Spain. ELRA Language Resource Association.
Cite (Informal):: VectorEdits: A Dataset and Benchmark for Instruction-Based Editing of Vector Graphics (Kuchar et al., LREC 2026)
Copy Citation:

External Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{kuchar-etal-2026-vectoredits,
    title = "{V}ector{E}dits: A Dataset and Benchmark for Instruction-Based Editing of Vector Graphics",
    author = "Kuchar, Josef  and
      Kadlcik, Marek  and
      Spiegel, Michal  and
      Stefanik, Michal",
    editor = "Piperidis, Stelios  and
      Bel, N{\'u}ria  and
      van den Heuvel, Henk  and
      Ide, Nancy  and
      Krek, Simon  and
      Toral, Antonio",
    booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://aclanthology.org/2026.lrec-1.868/",
    doi = "10.63317/5gc5ibtb5k8i",
    pages = "11119--11124",
    abstract = "We introduce a large-scale dataset for instruction-guided vector image editing, consisting of over 270,000 pairs of SVG images paired with natural language edit instructions. Our dataset enables training and evaluation of models that modify vector graphics based on textual commands. We describe the data collection process, including image pairing via CLIP similarity and instruction generation with vision-language models. Initial experiments with state-of-the-art large language models reveal that current methods struggle to produce accurate and valid edits, underscoring the challenge of this task. To foster research in natural language-driven vector graphic generation and editing, we make our resources created within this work publicly available."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kuchar-etal-2026-vectoredits">
    <titleInfo>
        <title>VectorEdits: A Dataset and Benchmark for Instruction-Based Editing of Vector Graphics</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Josef</namePart>
        <namePart type="family">Kuchar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Marek</namePart>
        <namePart type="family">Kadlcik</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Michal</namePart>
        <namePart type="family">Spiegel</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Michal</namePart>
        <namePart type="family">Stefanik</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Stelios</namePart>
            <namePart type="family">Piperidis</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Núria</namePart>
            <namePart type="family">Bel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Henk</namePart>
            <namePart type="family">van den Heuvel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nancy</namePart>
            <namePart type="family">Ide</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Simon</namePart>
            <namePart type="family">Krek</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Antonio</namePart>
            <namePart type="family">Toral</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>ELRA Language Resource Association</publisher>
            <place>
                <placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We introduce a large-scale dataset for instruction-guided vector image editing, consisting of over 270,000 pairs of SVG images paired with natural language edit instructions. Our dataset enables training and evaluation of models that modify vector graphics based on textual commands. We describe the data collection process, including image pairing via CLIP similarity and instruction generation with vision-language models. Initial experiments with state-of-the-art large language models reveal that current methods struggle to produce accurate and valid edits, underscoring the challenge of this task. To foster research in natural language-driven vector graphic generation and editing, we make our resources created within this work publicly available.</abstract>
    <identifier type="citekey">kuchar-etal-2026-vectoredits</identifier>
    <identifier type="doi">10.63317/5gc5ibtb5k8i</identifier>
    <location>
        <url>https://aclanthology.org/2026.lrec-1.868/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>11119</start>
            <end>11124</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T VectorEdits: A Dataset and Benchmark for Instruction-Based Editing of Vector Graphics
%A Kuchar, Josef
%A Kadlcik, Marek
%A Spiegel, Michal
%A Stefanik, Michal
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F kuchar-etal-2026-vectoredits
%X We introduce a large-scale dataset for instruction-guided vector image editing, consisting of over 270,000 pairs of SVG images paired with natural language edit instructions. Our dataset enables training and evaluation of models that modify vector graphics based on textual commands. We describe the data collection process, including image pairing via CLIP similarity and instruction generation with vision-language models. Initial experiments with state-of-the-art large language models reveal that current methods struggle to produce accurate and valid edits, underscoring the challenge of this task. To foster research in natural language-driven vector graphic generation and editing, we make our resources created within this work publicly available.
%R 10.63317/5gc5ibtb5k8i
%U https://aclanthology.org/2026.lrec-1.868/
%U https://doi.org/10.63317/5gc5ibtb5k8i
%P 11119-11124

Download as File

Markdown (Informal)

[VectorEdits: A Dataset and Benchmark for Instruction-Based Editing of Vector Graphics](https://aclanthology.org/2026.lrec-1.868/) (Kuchar et al., LREC 2026)

VectorEdits: A Dataset and Benchmark for Instruction-Based Editing of Vector Graphics (Kuchar et al., LREC 2026)

ACL

Josef Kuchar, Marek Kadlcik, Michal Spiegel, and Michal Stefanik. 2026. VectorEdits: A Dataset and Benchmark for Instruction-Based Editing of Vector Graphics. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 11119–11124, Palma de Mallorca, Spain. ELRA Language Resource Association.