Saved in:
Bibliographic Details
Main Authors: Li, Zhifei, Chen, Lifan, Yi, Jiali, Hou, Xiaoju, Zhao, Yue, Huang, Wenxin, Zhang, Miao, Xiao, Kui, Yang, Bing
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.18709
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914213057789952
author Li, Zhifei
Chen, Lifan
Yi, Jiali
Hou, Xiaoju
Zhao, Yue
Huang, Wenxin
Zhang, Miao
Xiao, Kui
Yang, Bing
author_facet Li, Zhifei
Chen, Lifan
Yi, Jiali
Hou, Xiaoju
Zhao, Yue
Huang, Wenxin
Zhang, Miao
Xiao, Kui
Yang, Bing
contents Knowledge Tracing (KT) aims to dynamically model a student's mastery of knowledge concepts based on their historical learning interactions. Most current methods rely on single-point estimates, which cannot distinguish true ability from outburst or carelessness, creating ambiguity in judging mastery. To address this issue, we propose a Knowledge Mastery-State Disambiguation for Knowledge Tracing model (KeenKT), which represents a student's knowledge state at each interaction using a Normal-Inverse-Gaussian (NIG) distribution, thereby capturing the fluctuations in student learning behaviors. Furthermore, we design an NIG-distance-based attention mechanism to model the dynamic evolution of the knowledge state. In addition, we introduce a diffusion-based denoising reconstruction loss and a distributional contrastive learning loss to enhance the model's robustness. Extensive experiments on six public datasets demonstrate that KeenKT outperforms SOTA KT models in terms of prediction accuracy and sensitivity to behavioral fluctuations. The proposed method yields the maximum AUC improvement of 5.85% and the maximum ACC improvement of 6.89%.
format Preprint
id arxiv_https___arxiv_org_abs_2512_18709
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle KeenKT: Knowledge Mastery-State Disambiguation for Knowledge Tracing
Li, Zhifei
Chen, Lifan
Yi, Jiali
Hou, Xiaoju
Zhao, Yue
Huang, Wenxin
Zhang, Miao
Xiao, Kui
Yang, Bing
Artificial Intelligence
Knowledge Tracing (KT) aims to dynamically model a student's mastery of knowledge concepts based on their historical learning interactions. Most current methods rely on single-point estimates, which cannot distinguish true ability from outburst or carelessness, creating ambiguity in judging mastery. To address this issue, we propose a Knowledge Mastery-State Disambiguation for Knowledge Tracing model (KeenKT), which represents a student's knowledge state at each interaction using a Normal-Inverse-Gaussian (NIG) distribution, thereby capturing the fluctuations in student learning behaviors. Furthermore, we design an NIG-distance-based attention mechanism to model the dynamic evolution of the knowledge state. In addition, we introduce a diffusion-based denoising reconstruction loss and a distributional contrastive learning loss to enhance the model's robustness. Extensive experiments on six public datasets demonstrate that KeenKT outperforms SOTA KT models in terms of prediction accuracy and sensitivity to behavioral fluctuations. The proposed method yields the maximum AUC improvement of 5.85% and the maximum ACC improvement of 6.89%.
title KeenKT: Knowledge Mastery-State Disambiguation for Knowledge Tracing
topic Artificial Intelligence
url https://arxiv.org/abs/2512.18709