Summary of Evaluating the Application Of Large Language Models to Generate Feedback in Programming Education, by Sven Jacobs and Steffen Jaschke
Evaluating the Application of Large Language Models to Generate Feedback in Programming Education
by Sven Jacobs, Steffen Jaschke
First submitted to arxiv on: 13 Mar 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Human-Computer Interaction (cs.HC)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper presents a novel approach to enhancing programming education using large language models (LLMs) specifically GPT-4. A web application was designed to utilize GPT-4’s capabilities in providing feedback on programming tasks without revealing the solution. The study evaluated the application with 51 students over one semester, demonstrating that most of GPT-4’s feedback effectively addressed code errors. However, limitations emerged regarding incorrect suggestions and hallucinated issues, highlighting the need for further development. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about using a super smart computer program called GPT-4 to help people learn programming better. The researchers made an online tool that uses GPT-4 to give feedback on programming tasks without giving away the answers. They tested this tool with 51 students and found that most of the time, the feedback was helpful in fixing code errors. However, there were some problems with incorrect suggestions and false issues, which need to be fixed. |
Keywords
» Artificial intelligence » Gpt
