Assessing LLMs for Front-end Software Architecture Knowledge

TL;DR

This paper evaluates ChatGPT 4 Turbo's ability to understand, analyze, and generate iOS architecture structures, revealing strengths in higher-order tasks and challenges in detailed retrieval, and proposes a benchmark for LLMs in software design.

Contribution

It introduces a comprehensive evaluation framework based on Bloom's taxonomy and proposes a benchmark for assessing LLMs in software architecture tasks.

Findings

LLMs excel in evaluating and creating architecture components.

Challenges remain in retrieving precise architectural details.

The study highlights potential and barriers of LLMs in software design.

Abstract

Large Language Models (LLMs) have demonstrated significant promise in automating software development tasks, yet their capabilities with respect to software design tasks remains largely unclear. This study investigates the capabilities of an LLM in understanding, reproducing, and generating structures within the complex VIPER architecture, a design pattern for iOS applications. We leverage Bloom's taxonomy to develop a comprehensive evaluation framework to assess the LLM's performance across different cognitive domains such as remembering, understanding, applying, analyzing, evaluating, and creating. Experimental results, using ChatGPT 4 Turbo 2024-04-09, reveal that the LLM excelled in higher-order tasks like evaluating and creating, but faced challenges with lower-order tasks requiring precise retrieval of architectural details. These findings highlight both the potential of LLMs to reduce development costs and the barriers to their effective application in real-world software design scenarios. This study proposes a benchmark format for assessing LLM capabilities in software architecture, aiming to contribute toward more robust and accessible AI-driven development tools.