Explaining Code Examples in Introductory Programming Courses: LLM vs Humans

Arun Balajiee Lekshmi Narayanan, Priti Oli, Jeevan Chapagain, Mohammad Hassany, Rabin Banjade, Peter Brusilovsky, Vasile Rus

Track: Innovations in AI for Education (Day 1)

Paper Length: long-paper (6 pages + references)

Keywords: Programming, Self--Explanations, ChatGPT

TL;DR: This work explores the idea of using LLMs to explain source code and compare with other data colleced by research team

Abstract:

Worked examples, which present an explained code for solving typical programming problems are among the most popular types of learning content in programming classes. Most approaches and tools for presenting these examples to students are based on line-by-line
explanations of the example code. However, instructors rarely have time to provide explanations for many examples typically used in a programming class. In this paper, we assess the feasibility of using LLMs to generate code explanations for passive and active example
exploration systems. To achieve this goal, we compare the code explanations generated by chatGPT with the explanations generated by both experts and students.

Submission Number: 6