Analysis on LLMs Performance for Code Summarization

Abstract

The goal of code summarizing is to produce concise source code descriptions in natural language. Deep learning has been used more and more recently in software engineering, particularly for tasks like code creation and summarization. Specifically, it appears that the most current Large Language Models with coding perform well on these tasks. Code summarization has evolved tremendously with the advent of Large Language Models (LLMs), providing sophisticated methods for generating concise and accurate summaries of source code. Our study aims to perform a comparative analysis of several open-source LLMs, namely LLaMA-3, Phi-3, Mistral, and Gemma. These models’ performance is assessed using important metrics such as BLEU3.1 and ROUGE3.2 . Through this analysis, we seek to identify the strengths and weaknesses of each model, offering insights into their applicability and effectiveness in code summarization tasks. Our findings contribute to the ongoing development and refinement of LLMs, supporting their integration into tools that enhance software development and maintenance processes.