RegKT: Interpretable and Robust Deep Knowledge Tracing With IRT-Regularizer

Samuel Girard; Juan D. Pinto; Jill-Jênn Vie; Amel Bouzeghoub

cs.LGSep 18, 2026

RegKT: Interpretable and Robust Deep Knowledge Tracing With IRT-Regularizer

Authors: Samuel Girard, Juan D. Pinto, Jill-Jênn Vie, Amel Bouzeghoub

Organizations: Inria-Saclay · University of Illinois Urbana-Champaign, Urbana, IL, USA · Telecom-Sud Paris

Abstract

As deep learning models continue to advance, knowledge tracing models have achieved higher accuracy. However, these gains come at the cost of reduced interpretability, which is crucial for practitioners in educational settings to adopt new methodologies. Additionally, deep learning models are prone to overfitting, particularly when dealing with the small datasets that are common in educational applications. In this paper, we propose a novel regularization technique designed to enhance the robustness of deep-learning-based knowledge tracing models, while simultaneously improving their interpretability. Our method addresses both the interpretability and overfitting challenges, making it more feasible for real-world educational applications.

Figures & tables

Figure 1: The connection between variables in RegKT. The input ( $x_{t}$ ) is either a one-hot encoding or compressed representation of student action, and the prediction ( $y_{t}$ ) is a probability vector for answering each problem correctly, with $(v_{t})$ as the student’s proficiency parameter estimate.

Dataset	Model	AUC	Accuracy
Fraction	DKT	0.879	0.805
	RegKT	0.889	0.812
	IRT	0.656	0.615
RoboMission	DKT	0.835	0.898
	RegKT	0.838	0.9015
	IRT	0.786	0.890

Table 1: Results in AUC and accuracy (Acc.) for all datasets.

Panel of Figure 2 — Figure 2: Visualization of the weights linking the hidden state to item correctness, with each label associated with the ordering of difficulties.

Panel of Figure 3 — Figure 3: Visualization of the hidden state clusters in classical DKT (top) vs. RegKT (bottom) in fraction. We select subsets of top, middle, and low-performing students (based on their IRT ability)

Panel of Figure 4 — Figure 4: Visualization of the hidden-state clusters in classical DKT (top) vs. RegKT (bottom) in RoboMission.

Figure 5: Alignment of the hidden state with its proficiency parameter in ASSISTments: $h_{T_{i}}$ associated to higher proficiency parameter $v_{T_{i}}$ are on the top right of the plot

Figure 6: Illustration of the AUC curve, where students interact with exercises generated under the M-IRT model. Here $\epsilon=0$ implies the DKT model

Figure 7: Evolution of the proficiency parameter for a student in the test set. The red dotted line represents a ground-truth proficiency parameter for the student

Knowledge Tracing

Knowledge tracing models how learners’ mastery of skills changes over time from their interactions with educational tasks.

See all 31 papers

MERIT: Memory-Enhanced Retrieval for Interpretable Knowledge Tracing
Mar 3, 2026Runze Li, Kedi Chen, Guwei Feng +3Knowledge Tracing Educational Technology
School of Computer Science and Technology, East China Normal University, China · Shanghai Innovation Institute, China · WeChat AI, Tencent, China
Neural-Symbolic Knowledge Tracing: Injecting Educational Knowledge into Deep Learning for Responsible Learner Modelling
Apr 9, 2026Danial Hooshyar, Gustav Šír, Yeongwook Yang +6Knowledge Tracing AI in Education
School of Digital Technologies Tallinn University, Estonia · Faculty of Information Technology University of Jyväskylä Finland · Faculty of Education and Psychology University of Jyväskylä Finland +7
Explainable Knowledge Tracing via Probabilistic Embeddings and Pattern-based Reasoning
May 10, 2026Siyu Wu, Cong Xu, Wei ZhangRepresentation Learning Interpretable ML
1Shanghai Institute of AI Education, East China Normal University, Shanghai, 200241, China · 2Shool of Computer Sicence and Technology, East China Normal University, Shanghai, 200241, China

Mar 3, 2026J/K move · Enter open · S save

MERIT: Memory-Enhanced Retrieval for Interpretable Knowledge Tracing

Runze Li, Kedi Chen, Guwei Feng, Mo Yu+2

School of Computer Science and Technology, East China Normal University, China · Shanghai Innovation Institute, China · WeChat AI, Tencent, China

Knowledge Tracing Educational Technology Retrieval-Augmented Generation

Open paper AskPDF arXiv

Knowledge Tracing (KT) models students' evolving knowledge states to predict future performance, serving as a foundation for personalized education. While traditional deep learning models achieve high accuracy, they often lack interpretability. Large Language Models (LLMs) offer strong reasoning capabilities but struggle with limited context windows and hallucinations. Furthermore, existing LLM-based methods typically require expensive fine-tuning, limiting scalability and adaptability to new data. We propose MERIT (Memory-Enhanced Retrieval for Interpretable Knowledge Tracing), a training-free framework combining frozen LLM reasoning with structured pedagogical memory. Rather than updating parameters, MERIT transforms raw interaction logs into an interpretable memory bank. The framework uses semantic denoising to categorize students into latent cognitive schemas and constructs a paradigm bank where representative error patterns are analyzed offline to generate explicit Chain-of-Thought (CoT) rationales. During inference, a hierarchical routing mechanism retrieves relevant contexts, while a logic-augmented module applies semantic constraints to calibrate predictions. By grounding the LLM in interpretable memory, MERIT achieves state-of-the-art performance on real-world datasets without gradient updates. This approach reduces computational costs and supports dynamic knowledge updates, improving the accessibility and transparency of educational diagnosis.

Abstract

Knowledge Tracing

Explore similar work

MERIT: Memory-Enhanced Retrieval for Interpretable Knowledge Tracing

Neural-Symbolic Knowledge Tracing: Injecting Educational Knowledge into Deep Learning for Responsible Learner Modelling

Explainable Knowledge Tracing via Probabilistic Embeddings and Pattern-based Reasoning