activity
20242026
collaborators
Showing 2024Show all

11 papers · 1 filter

cs.SE2024

Overview of Web Application Performance Optimization Techniques

Juho Vepsäläinen, Arto Hellas, Petri Vuorimaa

During its thirty years of existence, the World Wide Web has helped to transform the world and create digital economies. Although it started as a global information exchange, it ha…

cs.AI2024

Evaluating Language Models for Generating and Judging Programming Feedback

Charles Koutcheme, Nicola Dainese, Arto Hellas +4

The emergence of large language models (LLMs) has transformed research and practice across a wide range of domains. Within the computing education research (CER) domain, LLMs have…

cs.CY2024

LLM-itation is the Sincerest Form of Data: Generating Synthetic Buggy Code Submissions for Computing Education

Juho Leinonen, Paul Denny, Olli Kiljunen +3

There is a great need for data in computing education research. Data is needed to understand how students behave, to train models of student behavior to optimally support students,…

cs.CY2024

On the Opportunities of Large Language Models for Programming Process Data

John Edwards, Arto Hellas, Juho Leinonen

Computing educators and researchers have used programming process data to understand how programs are constructed and what sorts of problems students struggle with. Although such d…

cs.CY2024

Comparing the Utility, Preference, and Performance of Course Material Search Functionality and Retrieval-Augmented Generation Large Language Model (RAG-LLM) AI Chatbots in Information-Seeking Tasks

Leonardo Pasquarelli, Charles Koutcheme, Arto Hellas

Providing sufficient support for students requires substantial resources, especially considering the growing enrollment numbers. Students need help in a variety of tasks, ranging f…

cs.CY2024

Synthetic Students: A Comparative Study of Bug Distribution Between Large Language Models and Computing Students

Stephen MacNeil, Magdalena Rogalska, Juho Leinonen +3

Large language models (LLMs) present an exciting opportunity for generating synthetic classroom data. Such data could include code containing a typical distribution of errors, simu…