Codehelp: Using large language models with guardrails for scalable support in programming classes

M Liffiton, BE Sheese, J Savelka, P Denny - Proceedings of the 23rd Koli …, 2023 - dl.acm.org
Computing educators face significant challenges in providing timely support to students,
especially in large class settings. Large language models (LLMs) have emerged recently …

The promise and challenges of generative AI in education

M Giannakos, R Azevedo, P Brusilovsky… - Behaviour & …, 2024 - Taylor & Francis
Generative artificial intelligence (GenAI) tools, such as large language models (LLMs),
generate natural language and other types of content to perform a wide range of tasks. This …

More robots are coming: large multimodal models (ChatGPT) can solve visually diverse images of Parsons problems

I Hou, O Man, S Mettille, S Gutierrez… - Proceedings of the 26th …, 2024 - dl.acm.org
Large language models are reshaping computing education. Based on recent research,
these models explain code better than students, answer multiple choice questions at or …

Decoding logic errors: a comparative study on bug detection by students and large language models

S MacNeil, P Denny, A Tran, J Leinonen… - Proceedings of the 26th …, 2024 - dl.acm.org
Identifying and resolving logic errors can be one of the most frustrating challenges for
novices programmers. Unlike syntax errors, for which a compiler or interpreter can issue a …

Evaluating Contextually Personalized Programming Exercises Created with Generative AI

E Logacheva, A Hellas, J Prather, S Sarsa… - Proceedings of the …, 2024 - dl.acm.org
Programming skills are typically developed through completing various hands-on exercises.
Such programming problems can be contextualized to students' interests and cultural …

Combining LLM-generated and test-based feedback in a MOOC for programming

H Gabbay, A Cohen - Proceedings of the Eleventh ACM Conference on …, 2024 - dl.acm.org
In large-scale programming courses, providing learners with immediate and effective
feedback is a significant challenge. This study explores the potential of Large Language …

Open Source Language Models Can Provide Feedback: Evaluating LLMs' Ability to Help Students Using GPT-4-As-A-Judge

C Koutcheme, N Dainese, S Sarsa, A Hellas… - Proceedings of the …, 2024 - dl.acm.org
Large language models (LLMs) have shown great potential for the automatic generation of
feedback in a wide range of computing contexts. However, concerns have been voiced …

Revisiting Unnaturalness for Automated Program Repair in the Era of Large Language Models

AZH Yang, S Kolak, VJ Hellendoorn, R Martins… - arXiv preprint arXiv …, 2024 - arxiv.org
Language models have improved by orders of magnitude with the recent emergence of
Transformer-based Large Language Models (LLMs). LLMs have demonstrated their ability …

On the Opportunities of Large Language Models for Programming Process Data

J Edwards, A Hellas, J Leinonen - arXiv preprint arXiv:2411.00414, 2024 - arxiv.org
Computing educators and researchers have used programming process data to understand
how programs are constructed and what sorts of problems students struggle with. Although …

Benchmarking Educational Program Repair

C Koutcheme, N Dainese, S Sarsa, J Leinonen… - arXiv preprint arXiv …, 2024 - arxiv.org
The emergence of large language models (LLMs) has sparked enormous interest due to
their potential application across a range of educational tasks. For example, recent work in …