Universities worldwide struggle with maintaining academic integrity due to the rise of advanced large language models (LLM) capable of generating flawless source code. Teachers need to be able to identify artificial intelligence (AI)-generated source code in student submissions accurately. There are already multiple different tools for detecting AI-generated content. Yet teachers are not using these tools. For this reason, this case study will focus on creating a prototype for automating the process of checking for AI-generated source code in submitted assignments in programming courses. Teachers at Linnaeus University (LNU) are using GitLab for submissions of programming assignments. The prototype in this case study will be created on GitLab and tested on submitted test assignments using the same structure utilized by teachers at LNU for their programming courses. The automated process will be accomplished using continuous integration (CI) pipelines on GitLab that will execute Python files that send and receive data to and from the AI-detection tool’s application programming interface (API). The received data will be represented on GitLab for teachers and students to see.
| Identifer | oai:union.ndltd.org:UPSALLA1/oai:DiVA.org:lnu-130306 |
| Date | January 2024 |
| Creators | Pirntke, Erik, Rindebrant, Wictor |
| Publisher | Linnéuniversitetet, Institutionen för datavetenskap och medieteknik (DM) |
| Source Sets | DiVA Archive at Upsalla University |
| Language | English |
| Detected Language | English |
| Type | Student thesis, info:eu-repo/semantics/bachelorThesis, text |
| Format | application/pdf |
| Rights | info:eu-repo/semantics/openAccess |
Page generated in 0.0019 seconds