Enregistré dans:
Détails bibliographiques
Auteurs principaux: Heickal, Hasnain, Lan, Andrew
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2502.19407
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866918004992770048
author Heickal, Hasnain
Lan, Andrew
author_facet Heickal, Hasnain
Lan, Andrew
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_19407
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Code-Edit Embedding to Model Student Debugging Behavior
Heickal, Hasnain
Lan, Andrew
Software Engineering
Computation and Language
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.
title Learning Code-Edit Embedding to Model Student Debugging Behavior
topic Software Engineering
Computation and Language
url https://arxiv.org/abs/2502.19407