Explainable Knowledge Tracing via Probabilistic Embeddings and Pattern-based Reasoning

• URL: http://arxiv.org/abs/2605.09369v1
• Date: Sun, 10 May 2026 06:41:58 GMT
• Title: Explainable Knowledge Tracing via Probabilistic Embeddings and Pattern-based Reasoning
• Abstract summary: Knowledge Tracing (KT) models students' knowledge states based on learning interactions to predict performance.<n>We propose Probabilistic Logical Knowledge Tracing (PLKT), an interpretable KT framework that formulates prediction as a goal-conditioned evidence reasoning process over historical learning behaviors.<n>PLKT outperforms state-of-the-art KT methods while achieving superior interpretability.
• Score: 14.812722196795827
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Knowledge Tracing (KT) models students' knowledge states based on learning interactions to predict performance. While deep learning-based KT models have boosted predictive accuracy, most models rely on deterministic vector embeddings and opaque latent state transitions, limiting interpretability regarding how specific past behaviors influence predictions. To address this limitation, we propose Probabilistic Logical Knowledge Tracing (PLKT), an interpretable KT framework that formulates prediction as a goal-conditioned evidence reasoning process over historical learning behaviors. Instead of representing knowledge states as deterministic vector embeddings, PLKT employs robust Beta-distributed probabilistic embeddings to represent student knowledge states. This probabilistic foundation allows us to model the uncertainty of historical behaviors and perform explicit logical operations (e.g., conjunction), constructing transparent reasoning paths that reveal how specific past interactions contribute to the prediction. Extensive experiments show that PLKT outperforms state-of-the-art KT methods while achieving superior interpretability. Our code is available at https://anonymous.4open.science/r/PLKT-D3CE/.

Related papers

• Disentangling Knowledge States with Ability and Proficiency Modeling for Knowledge Tracing [6.399286079325182]
  Knowledge tracing aims to predict students' future performance by modeling their evolving knowledge states from historical interactions.<n>We propose Phase-Aware Knowledge Tracing (PAKT), a KT framework that decomposes student interactions into ability and proficiency phases.<n>Our method consistently outperforms representative baselines, with a maximum AUC gain of 1.33% and an average gain of 0.82%.
  arXiv  Detail & Related papers  (2026-07-14T09:11:59Z)
• StanBKT: Rethinking Parameter Estimation in Bayesian Knowledge Tracing [0.0]
  We introduce StanBKT, an open-source Python package for estimating Bayesian Knowledge Tracing models.<n>StanBKT provides a unified framework supporting Hamiltonian Monte Carlo, variational inference, Pathfinder, and optimization-based estimation.<n>We evaluate StanBKT on large-scale observational and controlled educational datasets.
  arXiv  Detail & Related papers  (2026-05-21T21:27:10Z)
• DASKT: A Dynamic Affect Simulation Method for Knowledge Tracing [51.665582274736785]
  Knowledge Tracing (KT) predicts future performance by students' historical computation, and understanding students' affective states can enhance the effectiveness of KT.<n>We propose Affect Dynamic Knowledge Tracing (DASKT) to explore the impact of various student affective states on their knowledge states.<n>Our research highlights a promising avenue for future studies, focusing on achieving high interpretability and accuracy.
  arXiv  Detail & Related papers  (2025-01-18T10:02:10Z)
• Selective Temporal Knowledge Graph Reasoning [70.11788354442218]
  Temporal Knowledge Graph (TKG) aims to predict future facts based on given historical ones. Existing TKG reasoning models are unable to abstain from predictions they are uncertain. We propose an abstention mechanism for TKG reasoning, which helps the existing models make selective, instead of indiscriminate, predictions.
  arXiv  Detail & Related papers  (2024-04-02T06:56:21Z)
• Temporal Knowledge Graph Forecasting Without Knowledge Using In-Context Learning [23.971206470486468]
  We present a framework that converts relevant historical facts into prompts and generates ranked predictions using token probabilities. Surprisingly, we observe that LLMs, out-of-the-box, perform on par with state-of-the-art TKG models. We also discover that using numerical indices instead of entity/relation names, does not significantly affect the performance.
  arXiv  Detail & Related papers  (2023-05-17T23:50:28Z)
• B-Learner: Quasi-Oracle Bounds on Heterogeneous Causal Effects Under Hidden Confounding [51.74479522965712]
  We propose a meta-learner called the B-Learner, which can efficiently learn sharp bounds on the CATE function under limits on hidden confounding. We prove its estimates are valid, sharp, efficient, and have a quasi-oracle property with respect to the constituent estimators under more general conditions than existing methods.
  arXiv  Detail & Related papers  (2023-04-20T18:07:19Z)
• Improving Interpretability of Deep Sequential Knowledge Tracing Models with Question-centric Cognitive Representations [22.055683237994696]
  We present QIKT, a question-centric interpretable KT model to address the above challenges. The proposed QIKT approach explicitly models students' knowledge state variations at a fine-grained level. It outperforms a wide range of deep learning based KT models in terms of prediction accuracy with better model interpretability.
  arXiv  Detail & Related papers  (2023-02-14T08:14:30Z)
• Uncertainty estimation of pedestrian future trajectory using Bayesian approximation [137.00426219455116]
  Under dynamic traffic scenarios, planning based on deterministic predictions is not trustworthy. The authors propose to quantify uncertainty during forecasting using approximation which deterministic approaches fail to capture. The effect of dropout weights and long-term prediction on future state uncertainty has been studied.
  arXiv  Detail & Related papers  (2022-05-04T04:23:38Z)
• Knowledge-driven Active Learning [70.37119719069499]
  Active learning strategies aim at minimizing the amount of labelled data required to train a Deep Learning model. Most active strategies are based on uncertain sample selection, and even often restricted to samples lying close to the decision boundary. Here we propose to take into consideration common domain-knowledge and enable non-expert users to train a model with fewer samples.
  arXiv  Detail & Related papers  (2021-10-15T06:11:53Z)
• Enhancing Knowledge Tracing via Adversarial Training [5.461665809706664]
  We study the problem of knowledge tracing (KT) where the goal is to trace the students' knowledge mastery over time. Recent advances on KT have increasingly concentrated on exploring deep neural networks (DNNs) to improve the performance of KT. We propose an efficient AT based KT method (ATKT) to enhance KT model's generalization and thus push the limit of KT.
  arXiv  Detail & Related papers  (2021-08-10T03:35:13Z)
• Context-Aware Attentive Knowledge Tracing [21.397976659857793]
  We propose attentive knowledge tracing, which couples flexible attention-based neural network models with a series of novel, interpretable model components. AKT uses a novel monotonic attention mechanism that relates a learner's future responses to assessment questions to their past responses. We show that AKT outperforms existing KT methods (by up to $6%$ in AUC in some cases) on predicting future learner responses.
  arXiv  Detail & Related papers  (2020-07-24T02:45:43Z)
• Towards Interpretable Deep Learning Models for Knowledge Tracing [62.75876617721375]
  We propose to adopt the post-hoc method to tackle the interpretability issue for deep learning based knowledge tracing (DLKT) models. Specifically, we focus on applying the layer-wise relevance propagation (LRP) method to interpret RNN-based DLKT model. Experiment results show the feasibility using the LRP method for interpreting the DLKT model's predictions.
  arXiv  Detail & Related papers  (2020-05-13T04:03:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.