RAG-KT: Cross-platform Explainable Knowledge Tracing with Multi-view Fusion Retrieval Generation

TL;DR

RAG-KT introduces a retrieval-augmented approach using LLMs for cross-platform knowledge tracing, enhancing accuracy, robustness, and interpretability across diverse educational data sources.

Contribution

It presents a novel multi-view fusion retrieval generation framework that improves transferability and interpretability in knowledge tracing across heterogeneous platforms.

Findings

Achieves consistent accuracy improvements on three public benchmarks.

Demonstrates robustness under cross-platform distribution shifts.

Provides grounded, interpretable predictions for student performance.

Abstract

Knowledge Tracing (KT) infers a student's knowledge state from past interactions to predict future performance. Conventional Deep Learning (DL)-based KT models are typically tied to platform-specific identifiers and latent representations, making them hard to transfer and interpret. Large Language Model (LLM)-based methods can be either ungrounded under prompting or overly domain-dependent under fine-tuning. In addition, most existing KT methods are developed and evaluated under a same-distribution assumption. In real deployments, educational data often arise from heterogeneous platforms with substantial distribution shift, which often degrades generalization. To this end, we propose RAG-KT, a retrieval-augmented paradigm that frames cross-platform KT as reliable context constrained inference with LLMs. It builds a unified multi-source structured context with cross-source alignment via Question Group abstractions and retrieves complementary rich and reliable context for each prediction, enabling grounded prediction and interpretable diagnosis. Experiments on three public KT benchmarks demonstrate consistent gains in accuracy and robustness, including strong performance under cross-platform conditions.