WAFFLE: Finetuning Multi-Modal Models for Automated Front-End Development

TL;DR

This paper introduces Waffle, a fine-tuning strategy for large language models that enhances their ability to generate HTML from UI designs by incorporating structure-aware attention and contrastive learning, leading to significant performance improvements.

Contribution

Waffle is a novel fine-tuning approach that improves multi-modal model understanding of HTML structure and UI-image to HTML translation, outperforming existing methods.

Findings

Up to 9.00 percentage points higher HTML match

Significant improvements in CW-SSIM, CLIP, and LLEM metrics

Outperforms current fine-tuning methods on WebSight-Test and Design2Code benchmarks

Abstract

Web development involves turning UI designs into functional webpages, which can be difficult for both beginners and experienced developers due to the complexity of HTML's hierarchical structures and styles. While Large Language Models (LLMs) have shown promise in generating source code, two major challenges persist in UI-to-HTML code generation: (1) effectively representing HTML's hierarchical structure for LLMs, and (2) bridging the gap between the visual nature of UI designs and the text-based format of HTML code. To tackle these challenges, we introduce Waffle, a new fine-tuning strategy that uses a structure-aware attention mechanism to improve LLMs' understanding of HTML's structure and a contrastive fine-tuning approach to align LLMs' understanding of UI images and HTML code. Models fine-tuned with Waffle show up to 9.00 pp (percentage point) higher HTML match, 0.0982 higher CW-SSIM, 32.99 higher CLIP, and 27.12 pp higher LLEM on our new benchmark WebSight-Test and an existing benchmark Design2Code, outperforming current fine-tuning methods.