# Learning Code-Edit Embedding to Model Student Debugging Behavior

arXiv: https://arxiv.org/abs/2502.19407 · HTML: https://mlsanity.com/paper/2502.19407/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 23 references that are in the map.
- First posted on arXiv 26 Feb 2025.

## Builds on (most cited first, 11 of 11)

- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [CodeBLEU: a Method for Automatic Evaluation of Code Synthesis](https://mlsanity.com/paper/2009.10297/) (2020)
- [Large Language Models (GPT) for automating feedback on programming assignments](https://mlsanity.com/paper/2307.00150/) (2023)
- [Automating Human Tutor-Style Programming Feedback: Leveraging GPT-4 Tutor Model for Hint Generation and GPT-3.5 Student Model for Hint Validation](https://mlsanity.com/paper/2310.03780/) (2023)
- [Learning Program Embeddings to Propagate Feedback on Student Code](https://mlsanity.com/paper/1505.05969/) (2015)
- [Automated Personalized Feedback Improves Learning Gains in an Intelligent Tutoring System](https://mlsanity.com/paper/2005.02431/) (2020)
- [The Continuous Hint Factory - Providing Hints in Vast and Sparsely Populated Edit Distance Spaces](https://mlsanity.com/paper/1708.06564/) (2017)
- [Test Case-Informed Knowledge Tracing for Open-ended Coding Tasks](https://mlsanity.com/paper/2410.10829/) (2024)
- [Learning Off-By-One Mistakes: An Empirical Study](https://mlsanity.com/paper/2102.12429/) (2021)
- [Generating Feedback-Ladders for Logical Errors in Programming using Large Language Models](https://mlsanity.com/paper/2405.00302/) (2024)

## Built on by (most cited first, 1 of 1)

- [Modeling Student Learning with 3.8 Million Program Traces](https://mlsanity.com/paper/2510.05056/) (2025)

## Abstract (arXiv)

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.