Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Goodfellow, Martin, Booth, Robbie, Fagan, Andrew, Lambert, Alasdair
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2505.16430
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910961857724416
author Goodfellow, Martin
Booth, Robbie
Fagan, Andrew
Lambert, Alasdair
author_facet Goodfellow, Martin
Booth, Robbie
Fagan, Andrew
Lambert, Alasdair
contents Students often do not fully understand the code they have written. This sometimes does not become evident until later in their education, which can mean it is harder to fix their incorrect knowledge or misunderstandings. In addition, being able to fully understand code is increasingly important in a world where students have access to generative artificial intelligence (GenAI) tools, such as GitHub Copilot. One effective solution is to utilise code comprehension questions, where a marker asks questions about a submission to gauge understanding, this can also have the side effect of helping to detect plagiarism. However, this approach is time consuming and can be difficult and/or expensive to scale. This paper introduces AutoMCQ, which uses GenAI for the automatic generation of multiple-choice code comprehension questions. This is integrated with the CodeRunner automated assessment platform.
format Preprint
id arxiv_https___arxiv_org_abs_2505_16430
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AutoMCQ -- Automatically Generate Code Comprehension Questions using GenAI
Goodfellow, Martin
Booth, Robbie
Fagan, Andrew
Lambert, Alasdair
Software Engineering
Artificial Intelligence
Programming Languages
Students often do not fully understand the code they have written. This sometimes does not become evident until later in their education, which can mean it is harder to fix their incorrect knowledge or misunderstandings. In addition, being able to fully understand code is increasingly important in a world where students have access to generative artificial intelligence (GenAI) tools, such as GitHub Copilot. One effective solution is to utilise code comprehension questions, where a marker asks questions about a submission to gauge understanding, this can also have the side effect of helping to detect plagiarism. However, this approach is time consuming and can be difficult and/or expensive to scale. This paper introduces AutoMCQ, which uses GenAI for the automatic generation of multiple-choice code comprehension questions. This is integrated with the CodeRunner automated assessment platform.
title AutoMCQ -- Automatically Generate Code Comprehension Questions using GenAI
topic Software Engineering
Artificial Intelligence
Programming Languages
url https://arxiv.org/abs/2505.16430