DesignRepair: Dual-Stream Design Guideline-Aware Frontend Repair with Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yuan, Mingyue, Chen, Jieshan, Xing, Zhenchang, Quigley, Aaron, Luo, Yuyu, Luo, Tianqi, Mohammadi, Gelareh, Lu, Qinghua, Zhu, Liming
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909595232894976
author Yuan, Mingyue
Chen, Jieshan
Xing, Zhenchang
Quigley, Aaron
Luo, Yuyu
Luo, Tianqi
Mohammadi, Gelareh
Lu, Qinghua
Zhu, Liming
author_facet Yuan, Mingyue
Chen, Jieshan
Xing, Zhenchang
Quigley, Aaron
Luo, Yuyu
Luo, Tianqi
Mohammadi, Gelareh
Lu, Qinghua
Zhu, Liming
contents The rise of Large Language Models (LLMs) has streamlined frontend interface creation through tools like Vercel's V0, yet surfaced challenges in design quality (e.g., accessibility, and usability). Current solutions, often limited by their focus, generalisability, or data dependency, fall short in addressing these complexities. Moreover, none of them examine the quality of LLM-generated UI design. In this work, we introduce DesignRepair, a novel dual-stream design guideline-aware system to examine and repair the UI design quality issues from both code aspect and rendered page aspect. We utilised the mature and popular Material Design as our knowledge base to guide this process. Specifically, we first constructed a comprehensive knowledge base encoding Google's Material Design principles into low-level component knowledge base and high-level system design knowledge base. After that, DesignRepair employs a LLM for the extraction of key components and utilizes the Playwright tool for precise page analysis, aligning these with the established knowledge bases. Finally, we integrate Retrieval-Augmented Generation with state-of-the-art LLMs like GPT-4 to holistically refine and repair frontend code through a strategic divide and conquer approach. Our extensive evaluations validated the efficacy and utility of our approach, demonstrating significant enhancements in adherence to design guidelines, accessibility, and user experience metrics.
format Preprint
id arxiv_https___arxiv_org_abs_2411_01606
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DesignRepair: Dual-Stream Design Guideline-Aware Frontend Repair with Large Language Models
Yuan, Mingyue
Chen, Jieshan
Xing, Zhenchang
Quigley, Aaron
Luo, Yuyu
Luo, Tianqi
Mohammadi, Gelareh
Lu, Qinghua
Zhu, Liming
Software Engineering
D.2.2
The rise of Large Language Models (LLMs) has streamlined frontend interface creation through tools like Vercel's V0, yet surfaced challenges in design quality (e.g., accessibility, and usability). Current solutions, often limited by their focus, generalisability, or data dependency, fall short in addressing these complexities. Moreover, none of them examine the quality of LLM-generated UI design. In this work, we introduce DesignRepair, a novel dual-stream design guideline-aware system to examine and repair the UI design quality issues from both code aspect and rendered page aspect. We utilised the mature and popular Material Design as our knowledge base to guide this process. Specifically, we first constructed a comprehensive knowledge base encoding Google's Material Design principles into low-level component knowledge base and high-level system design knowledge base. After that, DesignRepair employs a LLM for the extraction of key components and utilizes the Playwright tool for precise page analysis, aligning these with the established knowledge bases. Finally, we integrate Retrieval-Augmented Generation with state-of-the-art LLMs like GPT-4 to holistically refine and repair frontend code through a strategic divide and conquer approach. Our extensive evaluations validated the efficacy and utility of our approach, demonstrating significant enhancements in adherence to design guidelines, accessibility, and user experience metrics.
title DesignRepair: Dual-Stream Design Guideline-Aware Frontend Repair with Large Language Models
topic Software Engineering
D.2.2
url https://arxiv.org/abs/2411.01606