Learning Code-Edit Embedding to Model Student Debugging Behavior
This work addresses the problem of personalized support in computer science education, though it is incremental as it builds on existing encoder-decoder and LLM methods.
The paper tackled the challenge of providing effective feedback for programming assignments by modeling student debugging behavior through code-edit embeddings, resulting in a model that excels at code reconstruction and personalized suggestions while uncovering common errors.
Providing effective feedback for programming assignments in computer science education can be challenging: students solve problems by iteratively submitting code, executing it, and using limited feedback from the compiler or the auto-grader to debug. Analyzing student debugging behavior in this process may reveal important insights into their knowledge and inform better personalized support tools. In this work, we propose an encoder-decoder-based model that learns meaningful code-edit embeddings between consecutive student code submissions, to capture their debugging behavior. Our model leverages information on whether a student code submission passes each test case to fine-tune large language models (LLMs) to learn code editing representations. It enables personalized next-step code suggestions that maintain the student's coding style while improving test case correctness. Our model also enables us to analyze student code-editing patterns to uncover common student errors and debugging behaviors, using clustering techniques. Experimental results on a real-world student code submission dataset demonstrate that our model excels at code reconstruction and personalized code suggestion while revealing interesting patterns in student debugging behavior.