Prompt Learning for Multi-Label Code Smell Detection: A Promising Approach

TL;DR

This paper introduces PromptSmell, a prompt learning-based method utilizing large language models to detect multi-label code smells, showing significant improvements over existing approaches in precision and F1 scores.

Contribution

The paper presents a novel prompt learning approach for multi-label code smell detection, transforming the problem into multi-classification with a customized answer space for LLMs.

Findings

PromptSmell improves precision by 11.17%.

PromptSmell enhances F1 score by 7.4%.

Effective multi-label code smell detection using prompt learning.

Abstract

Code smells indicate the potential problems of software quality so that developers can identify refactoring opportunities by detecting code smells. State-of-the-art approaches leverage heuristics, machine learning, and deep learning to detect code smells. However, existing approaches have not fully explored the potential of large language models (LLMs). In this paper, we propose \textit{PromptSmell}, a novel approach based on prompt learning for detecting multi-label code smell. Firstly, code snippets are acquired by traversing abstract syntax trees. Combined code snippets with natural language prompts and mask tokens, \textit{PromptSmell} constructs the input of LLMs. Secondly, to detect multi-label code smell, we leverage a label combination approach by converting a multi-label problem into a multi-classification problem. A customized answer space is added to the word list of pre-trained language models, and the probability distribution of intermediate answers is obtained by predicting the words at the mask positions. Finally, the intermediate answers are mapped to the target class labels by a verbalizer as the final classification result. We evaluate the effectiveness of \textit{PromptSmell} by answering six research questions. The experimental results demonstrate that \textit{PromptSmell} obtains an improvement of 11.17\% in $precision_{w}$ and 7.4\% in $F1_{w}$ compared to existing approaches.