WebGen-V Bench: Structured Representation for Enhancing Visual Design in LLM-based Web Generation and Evaluation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Kuang-Da, Wang, Zhao, Shimose, Yotaro, Wang, Wei-Yao, Takamatsu, Shingo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911216405839872
author Wang, Kuang-Da
Wang, Zhao
Shimose, Yotaro
Wang, Wei-Yao
Takamatsu, Shingo
author_facet Wang, Kuang-Da
Wang, Zhao
Shimose, Yotaro
Wang, Wei-Yao
Takamatsu, Shingo
contents Witnessed by the recent advancements on leveraging LLM for coding and multimodal understanding, we present WebGen-V, a new benchmark and framework for instruction-to-HTML generation that enhances both data quality and evaluation granularity. WebGen-V contributes three key innovations: (1) an unbounded and extensible agentic crawling framework that continuously collects real-world webpages and can leveraged to augment existing benchmarks; (2) a structured, section-wise data representation that integrates metadata, localized UI screenshots, and JSON-formatted text and image assets, explicit alignment between content, layout, and visual components for detailed multimodal supervision; and (3) a section-level multimodal evaluation protocol aligning text, layout, and visuals for high-granularity assessment. Experiments with state-of-the-art LLMs and ablation studies validate the effectiveness of our structured data and section-wise evaluation, as well as the contribution of each component. To the best of our knowledge, WebGen-V is the first work to enable high-granularity agentic crawling and evaluation for instruction-to-HTML generation, providing a unified pipeline from real-world data acquisition and webpage generation to structured multimodal assessment.
format Preprint
id arxiv_https___arxiv_org_abs_2510_15306
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle WebGen-V Bench: Structured Representation for Enhancing Visual Design in LLM-based Web Generation and Evaluation
Wang, Kuang-Da
Wang, Zhao
Shimose, Yotaro
Wang, Wei-Yao
Takamatsu, Shingo
Artificial Intelligence
Witnessed by the recent advancements on leveraging LLM for coding and multimodal understanding, we present WebGen-V, a new benchmark and framework for instruction-to-HTML generation that enhances both data quality and evaluation granularity. WebGen-V contributes three key innovations: (1) an unbounded and extensible agentic crawling framework that continuously collects real-world webpages and can leveraged to augment existing benchmarks; (2) a structured, section-wise data representation that integrates metadata, localized UI screenshots, and JSON-formatted text and image assets, explicit alignment between content, layout, and visual components for detailed multimodal supervision; and (3) a section-level multimodal evaluation protocol aligning text, layout, and visuals for high-granularity assessment. Experiments with state-of-the-art LLMs and ablation studies validate the effectiveness of our structured data and section-wise evaluation, as well as the contribution of each component. To the best of our knowledge, WebGen-V is the first work to enable high-granularity agentic crawling and evaluation for instruction-to-HTML generation, providing a unified pipeline from real-world data acquisition and webpage generation to structured multimodal assessment.
title WebGen-V Bench: Structured Representation for Enhancing Visual Design in LLM-based Web Generation and Evaluation
topic Artificial Intelligence
url https://arxiv.org/abs/2510.15306