Benchmarking Educational Program Repair
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917661828448256 |
|---|---|
| author | Koutcheme, Charles Dainese, Nicola Sarsa, Sami Leinonen, Juho Hellas, Arto Denny, Paul |
| author_facet | Koutcheme, Charles Dainese, Nicola Sarsa, Sami Leinonen, Juho Hellas, Arto Denny, Paul |
| contents | 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 programming education has used LLMs to generate learning resources, improve error messages, and provide feedback on code. However, one factor that limits progress within the field is that much of the research uses bespoke datasets and different evaluation metrics, making direct comparisons between results unreliable. Thus, there is a pressing need for standardization and benchmarks that facilitate the equitable comparison of competing approaches. One task where LLMs show great promise is program repair, which can be used to provide debugging support and next-step hints to students. In this article, we propose a novel educational program repair benchmark. We curate two high-quality publicly available programming datasets, present a unified evaluation procedure introducing a novel evaluation metric rouge@k for approximating the quality of repairs, and evaluate a set of five recent models to establish baseline performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_05347 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Benchmarking Educational Program Repair Koutcheme, Charles Dainese, Nicola Sarsa, Sami Leinonen, Juho Hellas, Arto Denny, Paul Software Engineering Artificial Intelligence Computation and Language Computers and Society 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 programming education has used LLMs to generate learning resources, improve error messages, and provide feedback on code. However, one factor that limits progress within the field is that much of the research uses bespoke datasets and different evaluation metrics, making direct comparisons between results unreliable. Thus, there is a pressing need for standardization and benchmarks that facilitate the equitable comparison of competing approaches. One task where LLMs show great promise is program repair, which can be used to provide debugging support and next-step hints to students. In this article, we propose a novel educational program repair benchmark. We curate two high-quality publicly available programming datasets, present a unified evaluation procedure introducing a novel evaluation metric rouge@k for approximating the quality of repairs, and evaluate a set of five recent models to establish baseline performance. |
| title | Benchmarking Educational Program Repair |
| topic | Software Engineering Artificial Intelligence Computation and Language Computers and Society |
| url | https://arxiv.org/abs/2405.05347 |