Publication Date
| In 2025 | 0 |
| Since 2024 | 0 |
| Since 2021 (last 5 years) | 1 |
| Since 2016 (last 10 years) | 1 |
| Since 2006 (last 20 years) | 1 |
Descriptor
| Computational Linguistics | 1 |
| Computer Science Education | 1 |
| Computer Software | 1 |
| Error Correction | 1 |
| Feedback (Response) | 1 |
| Intelligent Tutoring Systems | 1 |
| Introductory Courses | 1 |
| Natural Language Processing | 1 |
| Programming | 1 |
| Programming Languages | 1 |
| Quality Control | 1 |
| More ▼ | |
Source
| International Educational… | 1 |
Author
| Cambronero, José | 1 |
| Gulwani, Sumit | 1 |
| Kohn, Tobias | 1 |
| Majumdarm, Rupak | 1 |
| Phung, Tung | 1 |
| Singla, Adish | 1 |
| Soares, Gustavo | 1 |
Publication Type
| Reports - Evaluative | 1 |
| Speeches/Meeting Papers | 1 |
Education Level
Audience
Location
Laws, Policies, & Programs
Assessments and Surveys
What Works Clearinghouse Rating
Peer reviewed
Download full textPhung, Tung; Cambronero, José; Gulwani, Sumit; Kohn, Tobias; Majumdarm, Rupak; Singla, Adish; Soares, Gustavo – International Educational Data Mining Society, 2023
Large language models (LLMs), such as Codex, hold great promise in enhancing programming education by automatically generating feedback for students. We investigate using LLMs to generate feedback for fixing syntax errors in Python programs, a key scenario in introductory programming. More concretely, given a student's buggy program, our goal is…
Descriptors: Computational Linguistics, Feedback (Response), Programming, Computer Science Education
