Exploring Large Language Models for Code Explanation
Software Engineering
2023-10-26 v1 Artificial Intelligence
Information Retrieval
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.
Cite
@article{arxiv.2310.16673,
title = {Exploring Large Language Models for Code Explanation},
author = {Paheli Bhattacharya and Manojit Chakraborty and Kartheek N S N Palepu and Vikas Pandey and Ishan Dindorkar and Rakesh Rajpurohit and Rishabh Gupta},
journal= {arXiv preprint arXiv:2310.16673},
year = {2023}
}
Comments
Accepted at the Forum for Information Retrieval Evaluation 2023 (IRSE Track)