Følg
Nicola Dainese
Tittel
Sitert av
Sitert av
År
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, J Leinonen, P Denny
Proceedings of the 2024 on Innovation and Technology in Computer Science …, 2024
172024
In-context symbolic regression: Leveraging large language models for function discovery
M Merler, K Haitsiukevich, N Dainese, P Marttinen
arXiv preprint arXiv:2404.19094, 2024
72024
Benchmarking Educational Program Repair
C Koutcheme, N Dainese, S Sarsa, J Leinonen, A Hellas, P Denny
arXiv preprint arXiv:2405.05347, 2024
62024
Evaluating language models for generating and judging programming feedback
C Koutcheme, N Dainese, S Sarsa, A Hellas, J Leinonen, S Ashraf, ...
Proceedings of the 56th ACM Technical Symposium on Computer Science …, 2025
52025
Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search
N Dainese, M Merler, M Alakuijala, P Marttinen
38th Conference on Neural Information Processing Systems (NeurIPS 2024), 2024
52024
Using Program Repair as a Proxy for Language Models’ Feedback Ability in Programming Education
C Koutcheme, N Dainese, A Hellas
Workshop on Innovative Use of NLP for Building Educational Applications, 165-181, 2024
32024
Reader: Model-based language-instructed reinforcement learning
N Dainese, P Marttinen, A Ilin
Conference on Empirical Methods in Natural Language Processing, 16583-16599, 2023
32023
Can docstring reformulation with an LLM improve code generation?
N Dainese, A Ilin, P Marttinen
Proceedings of the 18th Conference of the European Chapter of the …, 2024
22024
In-Context Symbolic Regression: Leveraging Language Models for Function Discovery
M Merler, N Dainese, K Haitsiukevich
arXiv preprint arXiv:2404.19094, 2024
2024
Deep Reinforcement Learning methods for StarCraft II Learning Environment
N Dainese
2020
Systemet kan ikke utføre handlingen. Prøv på nytt senere.
Artikler 1–10