Zero-Shot Learning for Code Explanation Using LLM

This paper explores the development of a software code explanation generation tool using CodeLlema 13B Instruct model under zero-shot learning scheme. The generated code explanations are designed to enhance problem localization and comprehension within Nokia Mobile Networks Solutions’ SoC codebases. We assess the semantics and readability of the generated explanations through a human-annotated dataset crafted by SoC engineers within the Nokia group alongside publicly available Code-NL pair dataset from the CoNala Corpus.