Charlie Koutcheme

Charlie Koutcheme

AI in Education Researcher

Fine-Tuning Open-Source Models as a Viable Alternative to Proprietary LLMs for Explaining Compiler Messages
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
57th ACM Technical Symposium on Computer Science Education, February 2026 (SIGCSE TS 2026), February 2026
Aligning Small Language Models for Programming Feedback: Towards Scalable Coding Support in a Massive Global Course
Aligning Small Language Models for Programming Feedback: Towards Scalable Coding Support in a Massive Global Course
Charles Koutcheme, Juliette Woodrow, Chris Piech
57th ACM Technical Symposium on Computer Science Education, February 2026 (SIGCSE TS 2026), September 2025
Reinforcement Learning for Programming Feedback: Aligning Small Language Models Without Human Preferences
Reinforcement Learning for Programming Feedback: Aligning Small Language Models Without Human Preferences
Charles Koutcheme, Nicola Dainese, Arto Hellas
9th Educational Data Mining in Computer Science Education (CSEDM) Workshop, May 2025
Direct Repair Optimization: Training Small Language Models For Educational Program Repair Improves Feedback
Direct Repair Optimization: Training Small Language Models For Educational Program Repair Improves Feedback
Charles Koutcheme, Nicola Dainese, Arto Hellas
20th Workshop on Innovative Use of NLP for Building Educational Applications, May 2025
Evaluating Language Models for Generating and Judging Programming Feedback
Evaluating Language Models for Generating and Judging Programming Feedback
Charles Koutcheme, Nicola Dainese, Sami Sarsa, Arto Hellas, Juho Leinonen, Syed Ashraf, Paul Denny
56th ACM Technical Symposium on Computer Science Education, February 2025
Open Source Language Models Can Provide Feedback: Evaluating LLMs’ Ability to Help Students Using GPT-4-As-A-Judge
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
International Conference on Innovation and Technology in Computer Science Education, July 2024
Using Program Repair as a Proxy for Language Models’ Feedback Ability in Programming Education
Using Program Repair as a Proxy for Language Models’ Feedback Ability in Programming Education
Charles Koutcheme, Nicola Dainese, Arto Hellas
19th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2024), June 2024
Evaluating Distance Measures for Program Repair
Evaluating Distance Measures for Program Repair
Charles Koutcheme, Nicola Dainese, Sami Sarsa, Arto Hellas, Juho Leinonen, Paul Denny
ACM Conference on International Computing Education Research, 2023, September 2023
Training Language Models for Programming Feedback Using Automated Repair Tools
Training Language Models for Programming Feedback Using Automated Repair Tools
Charles Koutcheme
Artificial Intelligence in Education, June 2023
Automated Program Repair using Generative Models for Code Infilling
Automated Program Repair using Generative Models for Code Infilling
Charles Koutcheme, Sami Sarsa, Juho Leinonen, Arto Hellas, Paul Denny
Artificial Intelligence in Education, June 2023