WebWeaver: Style-Aware Webpage Generation with Style Contracts

Runchen Xu; Mengxiao Zhang; Yikai Gu; Jiamou Liu

WebWeaver: Style-Aware Webpage Generation with Style Contracts

Runchen Xu, Mengxiao Zhang, Yikai Gu, Jiamou Liu

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 PDF.)

Authors concatenated from the text boxes above:

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

Abstract

We study style-aware prompt-to-webpage generation: producing executable webpages that preserve content, functionality, and abstract aesthetic intent. We identify the design-intent bottleneck and introduce three components to address it: Web4Style, a brief-based diagnostic benchmark; WebWeaver, a shared-state framework that constructs and propagates an explicit style contract; and WebJudge, a structured multimodal evaluator for content, function, and visual aesthetics. Experiments across three backbone models show that WebWeaver improves over direct generation and representative web/code-generation agents in both automatic and human evaluation. These results highlight style contracts as a missing intermediate layer for reliable prompt-to-webpage generation.

Anthology ID:: 2026.findings-emnlp.582
Volume:: Findings of the Association for Computational Linguistics: EMNLP 2026
Month:: October
Year:: 2026
Address:: Budapest, Hungary
Editors:: Hung-Yi Lee, Sunipa Dev, Jessy Li, Desmond Elliott
Venue:: Findings
SIG:: SIGDAT
Publisher:: Association for Computational Linguistics
Note:
Pages:: 12283–12319
Language:
URL:: https://aclanthology.org/2026.findings-emnlp.582/
DOI:
Bibkey:
Cite (ACL):: Runchen Xu, Mengxiao Zhang, Yikai Gu, and Jiamou Liu. 2026. WebWeaver: Style-Aware Webpage Generation with Style Contracts. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 12283–12319, Budapest, Hungary. Association for Computational Linguistics.
Cite (Informal):: WebWeaver: Style-Aware Webpage Generation with Style Contracts (Xu et al., Findings 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.findings-emnlp.582.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{xu-etal-2026-webweaver,
    title = "{W}eb{W}eaver: Style-Aware Webpage Generation with Style Contracts",
    author = "Xu, Runchen  and
      Zhang, Mengxiao  and
      Gu, Yikai  and
      Liu, Jiamou",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-emnlp.582/",
    pages = "12283--12319",
    ISBN = "979-8-89176-462-0",
    abstract = "We study \textit{style-aware prompt-to-webpage generation}: producing executable webpages that preserve content, functionality, and abstract aesthetic intent. We identify the \textit{design-intent bottleneck} and introduce three components to address it: \textbf{Web4Style}, a brief-based diagnostic benchmark; \textbf{WebWeaver}, a shared-state framework that constructs and propagates an explicit \textit{style contract}; and \textbf{WebJudge}, a structured multimodal evaluator for content, function, and visual aesthetics. Experiments across three backbone models show that WebWeaver improves over direct generation and representative web/code-generation agents in both automatic and human evaluation. These results highlight style contracts as a missing intermediate layer for reliable prompt-to-webpage generation."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2026-webweaver">
    <titleInfo>
        <title>WebWeaver: Style-Aware Webpage Generation with Style Contracts</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Runchen</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mengxiao</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yikai</namePart>
        <namePart type="family">Gu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jiamou</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>We study style-aware prompt-to-webpage generation: producing executable webpages that preserve content, functionality, and abstract aesthetic intent. We identify the design-intent bottleneck and introduce three components to address it: Web4Style, a brief-based diagnostic benchmark; WebWeaver, a shared-state framework that constructs and propagates an explicit style contract; and WebJudge, a structured multimodal evaluator for content, function, and visual aesthetics. Experiments across three backbone models show that WebWeaver improves over direct generation and representative web/code-generation agents in both automatic and human evaluation. These results highlight style contracts as a missing intermediate layer for reliable prompt-to-webpage generation.</abstract>
    <identifier type="citekey">xu-etal-2026-webweaver</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.582/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>12283</start>
            <end>12319</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T WebWeaver: Style-Aware Webpage Generation with Style Contracts
%A Xu, Runchen
%A Zhang, Mengxiao
%A Gu, Yikai
%A Liu, Jiamou
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F xu-etal-2026-webweaver
%X We study style-aware prompt-to-webpage generation: producing executable webpages that preserve content, functionality, and abstract aesthetic intent. We identify the design-intent bottleneck and introduce three components to address it: Web4Style, a brief-based diagnostic benchmark; WebWeaver, a shared-state framework that constructs and propagates an explicit style contract; and WebJudge, a structured multimodal evaluator for content, function, and visual aesthetics. Experiments across three backbone models show that WebWeaver improves over direct generation and representative web/code-generation agents in both automatic and human evaluation. These results highlight style contracts as a missing intermediate layer for reliable prompt-to-webpage generation.
%U https://aclanthology.org/2026.findings-emnlp.582/
%P 12283-12319

Download as File

Markdown (Informal)

[WebWeaver: Style-Aware Webpage Generation with Style Contracts](https://aclanthology.org/2026.findings-emnlp.582/) (Xu et al., Findings 2026)

WebWeaver: Style-Aware Webpage Generation with Style Contracts (Xu et al., Findings 2026)

ACL

Runchen Xu, Mengxiao Zhang, Yikai Gu, and Jiamou Liu. 2026. WebWeaver: Style-Aware Webpage Generation with Style Contracts. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 12283–12319, Budapest, Hungary. Association for Computational Linguistics.