Conditioning generative models on pattern-based knowledge components extracted from student code via AST analysis produces worked examples with better topical focus and relevance to logical errors than unconditioned baselines.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.HC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Personalized Worked Example Generation from Student Code Submissions Using Pattern-based Knowledge Components
Conditioning generative models on pattern-based knowledge components extracted from student code via AST analysis produces worked examples with better topical focus and relevance to logical errors than unconditioned baselines.