Fine-tuning a 7B code model on real student submissions produces code that better matches student error patterns, style, and incremental revision trajectories than prompting-only models across two temporal resolutions.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ParaStudent: Generating and Evaluating Realistic Student Code by Teaching LLMs to Struggle
Fine-tuning a 7B code model on real student submissions produces code that better matches student error patterns, style, and incremental revision trajectories than prompting-only models across two temporal resolutions.