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

2026-04-12

AI Summary

This work addresses the limitations of existing knowledge tracing models, which rely on platform-specific identifiers, lack interpretability, and exhibit poor generalization under distribution shifts. To overcome these challenges, the authors propose RAG-KT, the first approach to integrate retrieval-augmented generation (RAG) into cross-platform knowledge tracing. RAG-KT aligns multi-source data through problem-group abstraction and constructs a unified, structured context via multi-view fusion retrieval, thereby providing large language models with reliable and complementary evidence for prediction. Evaluated on three public benchmarks, the method significantly improves both prediction accuracy and robustness, particularly excelling in cross-platform scenarios, while simultaneously enhancing model interpretability and generalization capabilities.

Technology Category

• Knowledge Representation and Reasoning: Knowledge Acquisition
• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust
• Machine Learning: Multimodal Learning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

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.

Problem

• Knowledge Tracing
• Cross-platform
• Distribution Shift
• Interpretability
• Transferability

Innovation

• Retrieval-Augmented Generation
• Knowledge Tracing
• Cross-platform Learning
• Multi-view Fusion
• Explainable AI