Personalized Worked Example Generation from Student Code Submissions Using Pattern-based Knowledge Components

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pitts, Griffin, Hoq, Muntasir, Brusilovsky, Peter, Norouzi, Narges, Hellas, Arto, Leinonen, Juho, Akram, Bita
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917461997125632
author Pitts, Griffin
Hoq, Muntasir
Brusilovsky, Peter
Norouzi, Narges
Hellas, Arto
Leinonen, Juho
Akram, Bita
author_facet Pitts, Griffin
Hoq, Muntasir
Brusilovsky, Peter
Norouzi, Narges
Hellas, Arto
Leinonen, Juho
Akram, Bita
contents Adaptive programming practice often relies on fixed libraries of worked examples and practice problems, which require substantial authoring effort and may not correspond well to the logical errors and partial solutions students produce while writing code. As a result, students may receive learning content that does not directly address the concepts they are working to understand, while instructors must either invest additional effort in expanding content libraries or accept a coarse level of personalization. We present an approach for knowledge-component (KC) guided educational content generation using pattern-based KCs extracted from student code. Given a problem statement and student submissions, our pipeline extracts recurring structural KC patterns from students' code through AST-based analysis and uses them to condition a generative model. In this study, we apply this approach to worked example generation, and compare baseline and KC-conditioned outputs through expert evaluation. Results suggest that KC-conditioned generation improves topical focus and relevance to students' underlying logical errors, providing evidence that KC-based steering of generative models can support personalized learning at scale.
format Preprint
id arxiv_https___arxiv_org_abs_2604_24758
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Personalized Worked Example Generation from Student Code Submissions Using Pattern-based Knowledge Components
Pitts, Griffin
Hoq, Muntasir
Brusilovsky, Peter
Norouzi, Narges
Hellas, Arto
Leinonen, Juho
Akram, Bita
Human-Computer Interaction
Artificial Intelligence
Computers and Society
Emerging Technologies
Machine Learning
Adaptive programming practice often relies on fixed libraries of worked examples and practice problems, which require substantial authoring effort and may not correspond well to the logical errors and partial solutions students produce while writing code. As a result, students may receive learning content that does not directly address the concepts they are working to understand, while instructors must either invest additional effort in expanding content libraries or accept a coarse level of personalization. We present an approach for knowledge-component (KC) guided educational content generation using pattern-based KCs extracted from student code. Given a problem statement and student submissions, our pipeline extracts recurring structural KC patterns from students' code through AST-based analysis and uses them to condition a generative model. In this study, we apply this approach to worked example generation, and compare baseline and KC-conditioned outputs through expert evaluation. Results suggest that KC-conditioned generation improves topical focus and relevance to students' underlying logical errors, providing evidence that KC-based steering of generative models can support personalized learning at scale.
title Personalized Worked Example Generation from Student Code Submissions Using Pattern-based Knowledge Components
topic Human-Computer Interaction
Artificial Intelligence
Computers and Society
Emerging Technologies
Machine Learning
url https://arxiv.org/abs/2604.24758