Explaining Code Examples in Introductory Programming Courses: LLM vs Humans

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lekshmi-Narayanan, Arun-Balajiee, Oli, Priti, Chapagain, Jeevan, Hassany, Mohammad, Banjade, Rabin, Brusilovsky, Peter, Rus, Vasile
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916156746498048
author Lekshmi-Narayanan, Arun-Balajiee
Oli, Priti
Chapagain, Jeevan
Hassany, Mohammad
Banjade, Rabin
Brusilovsky, Peter
Rus, Vasile
author_facet Lekshmi-Narayanan, Arun-Balajiee
Oli, Priti
Chapagain, Jeevan
Hassany, Mohammad
Banjade, Rabin
Brusilovsky, Peter
Rus, Vasile
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2403_05538
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Explaining Code Examples in Introductory Programming Courses: LLM vs Humans
Lekshmi-Narayanan, Arun-Balajiee
Oli, Priti
Chapagain, Jeevan
Hassany, Mohammad
Banjade, Rabin
Brusilovsky, Peter
Rus, Vasile
Computers and Society
Human-Computer Interaction
Software Engineering
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.
title Explaining Code Examples in Introductory Programming Courses: LLM vs Humans
topic Computers and Society
Human-Computer Interaction
Software Engineering
url https://arxiv.org/abs/2403.05538