This article explores the natural language generation capabilities of large language models
with application to the production of two types of learning resources common in …

Students sometimes manage to produce functionally correct program code while having a
fragile understanding of the related learning goals. Such unproductive success could be …

Students are able to produce correctly functioning program code even though they have a
fragile understanding of how it actually works. Questions derived automatically from …

In this paper, we explore the application of large language models (LLMs) for generating
code-tracing questions in introductory programming courses. We designed targeted prompts …

Recent research has explored the creation of questions from code submitted by students.
These Questions about Learners' Code (QLCs) are created through program analysis …

The concept of variables can be hard to grasp for novices. The Roles of Variables framework
has been found to enhance learning elementary programming. The 11 roles can describe all …

Motivation. Code reading skills are important for comprehension. Explain-in-plain-English
tasks (EiPE) are one type of reading exercises that show promising results on the ability of …

Code comprehension has been shown to be challenging and important for a positive
learning outcome. Students don't always understand the code they write. This has been …

Students typically must work on complex exercises if they are about to learn advanced
concepts of programming. Technology-enhanced assessment systems can not only be used …

A testagem de software é maioritariamente realizada em modo de black-box, isto é, sem
incorporar nos testes qualquer conhecimento relativo ao funcionamento interno de um …