Exploring Large Language Models for Code Explanation

2023/10/25 by Paheli Bhattacharya, Manojit Chakraborty, Bhattacharya, Paheli +11 · 1 citation
Computer Science · #Artificial Intelligence (cs.AI) #D.2.3 #FOS: Computer and information sciences #I.7 #Information Retrieval (cs.IR) #Natural Language Processing Techniques #Software Engineering (cs.SE) #Software Engineering Research #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2310.16673

openalex publication_date 2023/10/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Automating code documentation through explanatory text can prove highly beneficial in code understanding. Large Language Models (LLMs) have made remarkable strides in Natural Language Processing, especially within software engineering tasks such as code generation and code summarization. This study specifically delves into the task of generating natural-language summaries for code snippets, using various LLMs. The findings indicate that Code LLMs outperform their generic counterparts, and zero-shot methods yield superior results when dealing with datasets with dissimilar distributions between training and testing sets.

Cited by

• Cross-Task Benchmarking and Evaluation of General-Purpose and Code-Specific Large Language Models

Related

• Large Language Models for Code Summarization
• The Behavior of Large Language Models When Prompted to Generate Code Explanations
• Analysis on LLMs Performance for Code Summarization
• Source Code Summarization in the Era of Large Language Models
• Testing the Effect of Code Documentation on Large Language Model Code Understanding