From Prediction to Application: Language Model-based Code Knowledge Tracing with Domain Adaptive Pre-Training and Automatic Feedback System with Pedagogical Prompting for Comprehensive Programming Education

This paper introduces CodeLKT, a language model-based knowledge tracing system for programming education that predicts student performance and generates personalized feedback using large language models with pedagogical prompting strategies. The system combines predictive modeling with an automatic feedback generation system that provides hints, answer corrections, and scaffolded support based on student code submissions and learning history.

Knowledge Tracing (KT) is a critical component in online learning, but traditional approaches face limitations in interpretability and cross-domain adaptability. This paper introduces Language Model-based Code Knowledge Tracing (CodeLKT), an innovative application of Language model-based Knowledge Tracing (LKT) to programming education. CodeLKT leverages pre-trained language models to process learning data, demonstrating superior performance over existing KT and Code KT models. We explore Domain

Study Type

Source

Framework Categories

Tool Types

Tags