Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

11-2025

Abstract

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 finetuning 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

Discipline

Programming Languages and Compilers | Software Engineering

Research Areas

Intelligent Systems and Optimization

Areas of Excellence

Digital transformation

Publication

Proceedings of the 2nd ACM/IEEE International Conference on AI-powered Software, Seoul, AIware 2025, November 19-20

First Page

1

Last Page

6

City or Country

Seoul, Korea

Download

Share

COinS