Decoding Logic Errors: A Comparative Study on Bug Detection by Students and Large Language Models

November 27, 2023 Β· Declared Dead Β· πŸ› IFAC Symposium on Advances in Control Education

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Stephen MacNeil, Paul Denny, Andrew Tran, Juho Leinonen, Seth Bernstein, Arto Hellas, Sami Sarsa, Joanne Kim arXiv ID 2311.16017 Category cs.HC: Human-Computer Interaction Cross-listed cs.AI Citations 26 Venue IFAC Symposium on Advances in Control Education Last Checked 4 months ago
Abstract
Identifying and resolving logic errors can be one of the most frustrating challenges for novices programmers. Unlike syntax errors, for which a compiler or interpreter can issue a message, logic errors can be subtle. In certain conditions, buggy code may even exhibit correct behavior -- in other cases, the issue might be about how a problem statement has been interpreted. Such errors can be hard to spot when reading the code, and they can also at times be missed by automated tests. There is great educational potential in automatically detecting logic errors, especially when paired with suitable feedback for novices. Large language models (LLMs) have recently demonstrated surprising performance for a range of computing tasks, including generating and explaining code. These capabilities are closely linked to code syntax, which aligns with the next token prediction behavior of LLMs. On the other hand, logic errors relate to the runtime performance of code and thus may not be as well suited to analysis by LLMs. To explore this, we investigate the performance of two popular LLMs, GPT-3 and GPT-4, for detecting and providing a novice-friendly explanation of logic errors. We compare LLM performance with a large cohort of introductory computing students $(n=964)$ solving the same error detection task. Through a mixed-methods analysis of student and model responses, we observe significant improvement in logic error identification between the previous and current generation of LLMs, and find that both LLM generations significantly outperform students. We outline how such models could be integrated into computing education tools, and discuss their potential for supporting students when learning programming.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Human-Computer Interaction

Died the same way β€” πŸ‘» Ghosted