{
  "added_at": "2026-10-16",
  "arxiv_id": "2506.07818",
  "arxiv_version_reviewed": "v1",
  "authors": [
    "Zhiyu Lin",
    "Zhengda Zhou",
    "Zhiyuan Zhao",
    "Tianrui Wan",
    "Yilun Ma",
    "Junyu Gao",
    "Xuelong Li"
  ],
  "bibtex_url": "https://awesomerea.org/papers/citations/paper-webuibench.bib",
  "code_url": null,
  "date_basis": "ACL proceedings publication month.",
  "date_basis_zh": "采用 ACL 会议论文集的出版月份。",
  "date_precision": "month",
  "description_en": "Diagnoses webpage-to-code capability through visual perception, HTML programming, image-to-HTML understanding, and screenshot reconstruction tasks. It separates underlying skills using question-answer pairs derived from real websites.",
  "description_zh": "通过视觉感知、HTML 编程、图像与 HTML 对应理解，以及截图重建任务，诊断从网页界面生成代码的能力；利用来自真实网站的问答对，分别考察各项基础技能。",
  "doi": "10.18653/v1/2025.findings-acl.815",
  "entry_url": "https://awesomerea.org/papers/paper-webuibench/",
  "entry_url_zh": "https://awesomerea.org/zh/papers/paper-webuibench/",
  "evidence_urls": [
    "https://aclanthology.org/2025.findings-acl.815/",
    "https://aclanthology.org/2025.findings-acl.815.pdf",
    "https://arxiv.org/abs/2506.07818",
    "https://github.com/MAIL-Tele-AI/WebUIBench",
    "https://huggingface.co/datasets/Tele-AI-MAIL/WebUIBench"
  ],
  "first_arxiv_date": "2025-06-09",
  "id": "paper-webuibench",
  "json_url": "https://awesomerea.org/papers/paper-webuibench/record.json",
  "kind": "research",
  "markdown_url": "https://awesomerea.org/papers/paper-webuibench/index.md",
  "markdown_url_zh": "https://awesomerea.org/zh/papers/paper-webuibench/index.md",
  "metadata_notes": "The published ACL record supplies the bibliography; repository citation fields remain placeholders and the dataset card displays a different arXiv identifier. The author-linked repository is retained as a project link, not advertised as a runnable code release.",
  "metadata_notes_zh": "书目信息采用正式 ACL 记录；仓库引用字段仍是占位内容，数据集卡片显示的 arXiv 编号也不同。作者链接的仓库作为项目链接保留，不将其宣传为可运行的代码发布。",
  "pdf_url": "https://aclanthology.org/2025.findings-acl.815.pdf",
  "project_url": "https://github.com/MAIL-Tele-AI/WebUIBench",
  "publication_date": "2025-07",
  "publication_status": "conference-paper",
  "record_type": "paper",
  "runtime_tested": false,
  "scope_limitations_en": "Primarily evaluates visual and HTML reconstruction skills. The paper includes a preliminary interaction study, not a full workflow or backend-equivalence benchmark. The official repository currently exposes README and images but not the evaluation scripts described in its instructions.",
  "scope_limitations_zh": "主要评估视觉与 HTML 重建技能。论文虽含初步交互研究，但并非完整流程或后端等价评测。官方仓库目前提供 README 和图片，未提供说明中提及的评估脚本。",
  "targets": [
    "website"
  ],
  "title": "WebUIBench: A Comprehensive Benchmark for Evaluating Multimodal Large Language Models in WebUI-to-Code",
  "title_zh": "WebUIBench：评估多模态大语言模型从网页界面生成代码能力的综合基准",
  "url": "https://aclanthology.org/2025.findings-acl.815/",
  "venue": "Findings of ACL 2025",
  "verification": "source-reviewed",
  "verified_at": "2026-10-16",
  "why_fits_en": "Adds diagnostic evidence for screenshot-based website reconstruction, complementary to end-to-end Design2Code evaluation.",
  "why_fits_zh": "为基于截图的网站重建提供诊断性证据，与 Design2Code 的端到端评估互补。",
  "year": 2025
}