Charles Koutcheme

According to our database, Charles Koutcheme authored at least 21 papers between 2022 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

Teaching Language Models How to Code Like Learners: Conversational Serialization for Student Simulation.

Charles Koutcheme, Arto Hellas, Juho Leinonen

CoRR, April, 2026

Fine-Tuning Open-Source Models as a Viable Alternative to Proprietary LLMs for Explaining Compiler Messages.

Lorenzo Lee Solano, Charles Koutcheme, Juho Leinonen, Alexandra Vassar, Jake Renzella

Proceedings of the 57th ACM Technical Symposium on Computer Science Education V.1, 2026

Aligning Small Language Models for Programming Feedback: Towards Scalable Coding Support in a Massive Global Course.

Charles Koutcheme, Juliette Woodrow, Chris Piech

Proceedings of the 57th ACM Technical Symposium on Computer Science Education V.1, 2026

2025

Narrowing the Gap: Supervised Fine-Tuning of Open-Source LLMs as a Viable Alternative to Proprietary Models for Pedagogical Tools.

Lorenzo Lee Solano, Charles Koutcheme, Juho Leinonen, Alexandra Vassar, Jake Renzella

CoRR, July, 2025

Evaluating Language Models for Generating and Judging Programming Feedback.

Charles Koutcheme, Nicola Dainese, Sami Sarsa, Arto Hellas, Juho Leinonen, Syed Ashraf, Paul Denny

Proceedings of the 56th ACM Technical Symposium on Computer Science Education V. 1, 2025

Reinforcement Learning for Programming Feedback: Aligning Small Language Models Without Human Preferences.

Charles Koutcheme, Nicola Dainese, Arto Hellas

Proceedings of 9th Educational Data Mining in Computer Science Education (CSEDM) Workshop co-located with the 18th Educational Data Mining Conference (EDM 2025), 2025

Direct Repair Optimization: Training Small Language Models For Educational Program Repair Improves Feedback.

Charles Koutcheme, Nicola Dainese, Arto Hellas

Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications, 2025

2024

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

CoRR, 2024

Benchmarking Educational Program Repair.

Charles Koutcheme, Nicola Dainese, Sami Sarsa, Juho Leinonen, Arto Hellas, Paul Denny

CoRR, 2024

Propagating Large Language Models Programming Feedback.

Charles Koutcheme, Arto Hellas

Proceedings of the Eleventh ACM Conference on Learning @ Scale, 2024

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

Charles Koutcheme, Nicola Dainese, Sami Sarsa, Arto Hellas, Juho Leinonen, Paul Denny

Proceedings of the 2024 on Innovation and Technology in Computer Science Education V. 1, 2024

Let's Ask AI About Their Programs: Exploring ChatGPT's Answers To Program Comprehension Questions.

Teemu Lehtinen, Charles Koutcheme, Arto Hellas

Proceedings of the 46th International Conference on Software Engineering: Software Engineering Education and Training, 2024

Using Program Repair as a Proxy for Language Models' Feedback Ability in Programming Education.

Charles Koutcheme, Nicola Dainese, Arto Hellas

Proceedings of the 19th Workshop on Innovative Use of NLP for Building Educational Applications, 2024

2023

Evaluating Distance Measures for Program Repair.

Charles Koutcheme, Sami Sarsa, Juho Leinonen, Lassi Haaranen, Arto Hellas

Proceedings of the 2023 ACM Conference on International Computing Education Research, 2023

Exploring the Responses of Large Language Models to Beginner Programmers' Help Requests.

Arto Hellas, Juho Leinonen, Sami Sarsa, Charles Koutcheme, Lilja Kujanpää, Juha Sorva

Proceedings of the 2023 ACM Conference on International Computing Education Research, 2023

Automated Program Repair Using Generative Models for Code Infilling.

Charles Koutcheme, Sami Sarsa, Juho Leinonen, Arto Hellas, Paul Denny

Proceedings of the Artificial Intelligence in Education - 24th International Conference, 2023

Training Language Models for Programming Feedback Using Automated Repair Tools.

Charles Koutcheme

Proceedings of the Artificial Intelligence in Education - 24th International Conference, 2023

2022

Speeding Up Automated Assessment of Programming Exercises.

Sami Sarsa, Juho Leinonen, Charles Koutcheme, Arto Hellas

Proceedings of the UKICER 2022: The United Kingdom and Ireland Computing Education Research Conference, Dublin, Ireland, September 1, 2022

Towards Open Natural Language Feedback Generation for Novice Programmers using Large Language Models.

Charles Koutcheme

Proceedings of the Koli Calling '22: 22nd Koli Calling International Conference on Computing Education Research, 2022

Exploring How Students Solve Open-ended Assignments: A Study of SQL Injection Attempts in a Cybersecurity Course.

Charles Koutcheme, Artturi Tilanterä, Aleksi Peltonen, Arto Hellas, Lassi Haaranen

Proceedings of the ITiCSE 2022: Innovation and Technology in Computer Science Education, Dublin, Ireland, July 8, 2022

Methodological Considerations for Predicting At-risk Students.

Charles Koutcheme, Sami Sarsa, Arto Hellas, Lassi Haaranen, Juho Leinonen

Proceedings of the ACE '22: Australasian Computing Education Conference, Virtual Event, Australia, February 14, 2022