Interactions with Prompt Problems: A New Way to Teach Programming with Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Prather, James, Denny, Paul, Leinonen, Juho, Smith IV, David H., Reeves, Brent N., MacNeil, Stephen, Becker, Brett A., Luxton-Reilly, Andrew, Amarouche, Thezyrie, Kimmel, Bailey
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909077361131520
author Prather, James
Denny, Paul
Leinonen, Juho
Smith IV, David H.
Reeves, Brent N.
MacNeil, Stephen
Becker, Brett A.
Luxton-Reilly, Andrew
Amarouche, Thezyrie
Kimmel, Bailey
author_facet Prather, James
Denny, Paul
Leinonen, Juho
Smith IV, David H.
Reeves, Brent N.
MacNeil, Stephen
Becker, Brett A.
Luxton-Reilly, Andrew
Amarouche, Thezyrie
Kimmel, Bailey
contents Large Language Models (LLMs) have upended decades of pedagogy in computing education. Students previously learned to code through \textit{writing} many small problems with less emphasis on code reading and comprehension. Recent research has shown that free code generation tools powered by LLMs can solve introductory programming problems presented in natural language with ease. In this paper, we propose a new way to teach programming with Prompt Problems. Students receive a problem visually, indicating how input should be transformed to output, and must translate that to a prompt for an LLM to decipher. The problem is considered correct when the code that is generated by the student prompt can pass all test cases. In this paper we present the design of this tool, discuss student interactions with it as they learn, and provide insights into this new class of programming problems as well as the design tools that integrate LLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2401_10759
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Interactions with Prompt Problems: A New Way to Teach Programming with Large Language Models
Prather, James
Denny, Paul
Leinonen, Juho
Smith IV, David H.
Reeves, Brent N.
MacNeil, Stephen
Becker, Brett A.
Luxton-Reilly, Andrew
Amarouche, Thezyrie
Kimmel, Bailey
Human-Computer Interaction
Artificial Intelligence
Large Language Models (LLMs) have upended decades of pedagogy in computing education. Students previously learned to code through \textit{writing} many small problems with less emphasis on code reading and comprehension. Recent research has shown that free code generation tools powered by LLMs can solve introductory programming problems presented in natural language with ease. In this paper, we propose a new way to teach programming with Prompt Problems. Students receive a problem visually, indicating how input should be transformed to output, and must translate that to a prompt for an LLM to decipher. The problem is considered correct when the code that is generated by the student prompt can pass all test cases. In this paper we present the design of this tool, discuss student interactions with it as they learn, and provide insights into this new class of programming problems as well as the design tools that integrate LLMs.
title Interactions with Prompt Problems: A New Way to Teach Programming with Large Language Models
topic Human-Computer Interaction
Artificial Intelligence
url https://arxiv.org/abs/2401.10759