activity
20222024
most citedAutomatic Generation of Programming Exercises and Code Explanations using Large Language Models

473 citations · 773 across the 16 of their papers we have counts for

collaborators

18 papers

cs.CY2024

Integrating Natural Language Prompting Tasks in Introductory Programming Courses

Chris Kerslake, Paul Denny, David H Smith +4

Introductory programming courses often emphasize mastering syntax and basic constructs before progressing to more complex and interesting programs. This bottom-up approach can be f…

cs.HC20243 cited

Large Language Models Meet User Interfaces: The Case of Provisioning Feedback

Stanislav Pozdniakov, Jonathan Brazil, Solmaz Abdi +5

Incorporating Generative AI (GenAI) and Large Language Models (LLMs) in education can enhance teaching efficiency and enrich student learning. Current LLM usage involves conversati…

cs.CY20247 cited

Automating Personalized Parsons Problems with Customized Contexts and Concepts

Andre del Carpio Gutierrez, Paul Denny, Andrew Luxton-Reilly

Parsons problems provide useful scaffolding for introductory programming students learning to write code. However, generating large numbers of high-quality Parsons problems that ap…

cs.CY20246 cited

Enhancing Student Engagement in Large-Scale Capstone Courses: An Experience Report

Asma Shakil, Paul Denny

Computer science (CS) capstone courses offer students a valuable opportunity to gain hands-on experience in software development, practice essential soft skills, and enhance their…

cs.HC2024

"Like a Nesting Doll": Analyzing Recursion Analogies Generated by CS Students using Large Language Models

Seth Bernstein, Paul Denny, Juho Leinonen +5

Grasping complex computing concepts often poses a challenge for students who struggle to anchor these new ideas to familiar experiences and understandings. To help with this, a goo…

cs.SE2024

A Picture Is Worth a Thousand Words: Exploring Diagram and Video-Based OOP Exercises to Counter LLM Over-Reliance

Bruno Pereira Cipriano, Pedro Alves, Paul Denny

Much research has highlighted the impressive capabilities of large language models (LLMs), like GPT and Bard, for solving introductory programming exercises. Recent work has shown…