Envisioning Future Interactive Web Development: Editing Webpage with Natural Language

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dang, Truong Hai, Xiao, Jingyu, Huo, Yintong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909878548692992
author Dang, Truong Hai
Xiao, Jingyu
Huo, Yintong
author_facet Dang, Truong Hai
Xiao, Jingyu
Huo, Yintong
contents The evolution of web applications relies on iterative code modifications, a process that is traditionally manual and time-consuming. While Large Language Models (LLMs) can generate UI code, their ability to edit existing code from new design requirements (e.g., "center the logo") remains a challenge. This is largely due to the absence of large-scale, high-quality tuning data to align model performance with human expectations. In this paper, we introduce a novel, automated data generation pipeline that uses LLMs to synthesize a high-quality fine-tuning dataset for web editing, named Instruct4Edit. Our approach generates diverse instructions, applies the corresponding code modifications, and performs visual verification to ensure correctness. By fine-tuning models on Instruct4Edit, we demonstrate consistent improvement in translating human intent into precise, structurally coherent, and visually accurate code changes. This work provides a scalable and transparent foundation for natural language based web editing, demonstrating that fine-tuning smaller open-source models can achieve competitive performance with proprietary systems. We release all data, code implementations, and model checkpoints for reproduction.
format Preprint
id arxiv_https___arxiv_org_abs_2510_26516
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Envisioning Future Interactive Web Development: Editing Webpage with Natural Language
Dang, Truong Hai
Xiao, Jingyu
Huo, Yintong
Software Engineering
The evolution of web applications relies on iterative code modifications, a process that is traditionally manual and time-consuming. While Large Language Models (LLMs) can generate UI code, their ability to edit existing code from new design requirements (e.g., "center the logo") remains a challenge. This is largely due to the absence of large-scale, high-quality tuning data to align model performance with human expectations. In this paper, we introduce a novel, automated data generation pipeline that uses LLMs to synthesize a high-quality fine-tuning dataset for web editing, named Instruct4Edit. Our approach generates diverse instructions, applies the corresponding code modifications, and performs visual verification to ensure correctness. By fine-tuning models on Instruct4Edit, we demonstrate consistent improvement in translating human intent into precise, structurally coherent, and visually accurate code changes. This work provides a scalable and transparent foundation for natural language based web editing, demonstrating that fine-tuning smaller open-source models can achieve competitive performance with proprietary systems. We release all data, code implementations, and model checkpoints for reproduction.
title Envisioning Future Interactive Web Development: Editing Webpage with Natural Language
topic Software Engineering
url https://arxiv.org/abs/2510.26516