Enhancing Knowledge Tracing through Leakage-Free and Recency-Aware Embeddings

arXiv:2508.17092v3 Announce Type: replace-cross Abstract: Knowledge Tracing (KT) aims to predict a student's future performance based on their sequence of interactions with learning content. Many KT models rely on knowledge concepts (KCs), which represent the skills required for each item. However, some of these models are vulnerable to label leakage, a phenomenon in which the input data inadvertently reveal the correct answer, particularly in datasets with multiple KCs per question. We propose a straightforward yet effective solution to prevent label leakage by masking ground-truth labels during input embedding construction whenever such leakage could occur. To accomplish this, we introduce a dedicated MASK label, inspired by masked language modeling (e.g., BERT), to replace ground-truth labels. In addition, we introduce Recency Encoding, which encodes the step-wise distance between the current item and its most recent previous occurrence. This distance is important for modeling learning dynamics such as forgetting, which is a fundamental aspect of human learning, yet it is often overlooked in existing models. Recency Encoding demonstrates improved performance over traditional positional encodings on multiple KT benchmarks. We show that incorporating our embeddings into KT models such as DKT, DKT+, AKT, and SAKT consistently improves prediction accuracy across multiple benchmarks. The approach is both efficient and widely applicable.

Abstract:Knowledge Tracing (KT) aims to predict a student's future performance based on their sequence of interactions with learning content. Many KT models rely on knowledge concepts (KCs), which represent the skills required for each item. However, some of these models are vulnerable to label leakage, a phenomenon in which the input data inadvertently reveal the correct answer, particularly in datasets with multiple KCs per question. We propose a straightforward yet effective solution to prevent label leakage by masking ground-truth labels during input embedding construction whenever such leakage could occur. To accomplish this, we introduce a dedicated MASK label, inspired by masked language modeling (e.g., BERT), to replace ground-truth labels. In addition, we introduce Recency Encoding, which encodes the step-wise distance between the current item and its most recent previous occurrence. This distance is important for modeling learning dynamics such as forgetting, which is a fundamental aspect of human learning, yet it is often overlooked in existing models. Recency Encoding demonstrates improved performance over traditional positional encodings on multiple KT benchmarks. We show that incorporating our embeddings into KT models such as DKT, DKT+, AKT, and SAKT consistently improves prediction accuracy across multiple benchmarks. The approach is both efficient and widely applicable.

This version of the article has been accepted for publication, after peer review (when applicable) but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: this https URL

Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)

arXiv:2508.17092 [cs.CY]

(or arXiv:2508.17092v3 [cs.CY] for this version)

Badran, Y., Preisach, C. Enhancing Knowledge Tracing through Leakage-Free and Recency-Aware Embeddings. SN COMPUT. SCI. 7, 774 (2026)

https://doi.org/10.1007/s42979-026-05344-3 DOI(s) linking to related resources

analiza aiqbench

Enhancing Knowledge Tracing through Leakage-Free and Recency-Aware Embeddings

Subiecte conexe