LLM-Based Design Pattern Detection

TL;DR

This paper introduces a novel approach using Large Language Models to automatically detect design pattern instances in codebases, addressing limitations of traditional static analysis methods and aiding software development tasks.

Contribution

It presents a new LLM-based method for identifying design patterns, focusing on class roles, which enhances software understanding and maintenance.

Findings

Effective detection of design patterns across diverse codebases

Improved accuracy over traditional static analysis tools

Supports developers in refactoring and maintenance tasks

Abstract

Detecting design pattern instances in unfamiliar codebases remains a challenging yet essential task for improving software quality and maintainability. Traditional static analysis tools often struggle with the complexity, variability, and lack of explicit annotations that characterize real-world pattern implementations. In this paper, we present a novel approach leveraging Large Language Models to automatically identify design pattern instances across diverse codebases. Our method focuses on recognizing the roles classes play within the pattern instances. By providing clearer insights into software structure and intent, this research aims to support developers, improve comprehension, and streamline tasks such as refactoring, maintenance, and adherence to best practices.