@brusilovsky

Experiences from Using Code Explanations Generated by Large Language Models in a Web Software Development E-Book

, , , , , , , and . Proceedings of the 54th ACM Technical Symposium on Computer Science Education V. 1, page 931-937. ACM, (March 2023)
DOI: 10.1145/3545945.3569785

Abstract

Advances in natural language processing have resulted in large language models (LLMs) that can generate code and code explanations. In this paper, we report on our experiences generating multiple code explanation types using LLMs and integrating them into an interactive e-book on web software development. Three different types of explanations -- a line-by-line explanation, a list of important concepts, and a high-level summary of the code -- were created. Students could view explanations by clicking a button next to code snippets, which showed the explanation and asked about its utility. Our results show that all explanation types were viewed by students and that the majority of students perceived the code explanations as helpful to them. However, student engagement varied by code snippet complexity, explanation type, and code snippet length. Drawing on our experiences, we discuss future directions for integrating explanations generated by LLMs into CS classrooms.

Description

Experiences from Using Code Explanations Generated by Large Language Models in a Web Software Development E-Book | Proceedings of the 54th ACM Technical Symposium on Computer Science Education V. 1

Links and resources

Tags

community

  • @brusilovsky
  • @dblp
@brusilovsky's tags highlighted