Feedback-Generation for Programming Exercises With GPT-4

  • Ever since Large Language Models (LLMs) and related applications have become broadly available, several studies investigated their potential for assisting educators and supporting students in higher education. LLMs such as Codex, GPT-3.5, and GPT 4 have shown promising results in the context of large programming courses, where students can benefit from feedback and hints if provided timely and at scale. This paper explores the quality of GPT-4 Turbo's generated output for prompts containing both the programming task specification and a student's submission as input. Two assignments from an introductory programming course were selected, and GPT-4 was asked to generate feedback for 55 randomly chosen, authentic student programming submissions. The output was qualitatively analyzed regarding correctness, personalization, fault localization, and other features identified in the material. Compared to prior work and analyses of GPT-3.5, GPT-4 Turbo shows notable improvements. For example, the output is more structured and consistent. GPT-4Ever since Large Language Models (LLMs) and related applications have become broadly available, several studies investigated their potential for assisting educators and supporting students in higher education. LLMs such as Codex, GPT-3.5, and GPT 4 have shown promising results in the context of large programming courses, where students can benefit from feedback and hints if provided timely and at scale. This paper explores the quality of GPT-4 Turbo's generated output for prompts containing both the programming task specification and a student's submission as input. Two assignments from an introductory programming course were selected, and GPT-4 was asked to generate feedback for 55 randomly chosen, authentic student programming submissions. The output was qualitatively analyzed regarding correctness, personalization, fault localization, and other features identified in the material. Compared to prior work and analyses of GPT-3.5, GPT-4 Turbo shows notable improvements. For example, the output is more structured and consistent. GPT-4 Turbo can also accurately identify invalid casing in student programs' output. In some cases, the feedback also includes the output of the student program. At the same time, inconsistent feedback was noted such as stating that the submission is correct but an error needs to be fixed. The present work increases our understanding of LLMs' potential, limitations, and how to integrate them into e-assessment systems, pedagogical scenarios, and instructing students who are using applications based on GPT-4.show moreshow less

Export metadata

Additional Services

Search Google Scholar
Metadaten
Author:Imen AzaizORCiD, Natalie KieslerORCiD, Sven StrickrothORCiD
DOI:https://doi.org/10.1145/3649217.3653594
Parent Title (English):Proceedings of the 2024 on Innovation and Technology in Computer Science Education Vol. 1
Publisher:ACM
Place of publication:New York, NY, USA
Document Type:conference proceeding (article)
Language:English
Date of first Publication:2024/07/03
Reviewed:Begutachtet/Reviewed
Release Date:2024/12/18
Pagenumber:7
First Page:31
Last Page:37
institutes:Fakultät Informatik
Research Themes:Digitalisierung & Künstliche Intelligenz
Verstanden ✔
Diese Webseite verwendet technisch erforderliche Session-Cookies. Durch die weitere Nutzung der Webseite stimmen Sie diesem zu. Unsere Datenschutzerklärung finden Sie hier.