Uncertainty-preserving deep knowledge tracing with state-space models

TL;DR

This paper introduces Dynamic LENS, a novel deep learning model that combines Bayesian state-space models with variational autoencoders to quantify student knowledge and uncertainty over time, bridging formative and summative assessment approaches.

Contribution

Dynamic LENS is the first model to integrate uncertainty preservation with flexible knowledge tracing using a Bayesian state-space framework in deep learning.

Findings

Similar predictive performance to existing models

Preserves epistemic uncertainty in student knowledge estimates

Bridges gap between formative and summative assessment models

Abstract

A central goal of both knowledge tracing and traditional assessment is to quantify student knowledge and skills at a given point in time. Deep knowledge tracing flexibly considers a student's response history but does not quantify epistemic uncertainty, while IRT and CDM compute measurement error but only consider responses to individual tests in isolation from a student's past responses. Elo and BKT could bridge this divide, but the simplicity of the underlying models limits information sharing across skills and imposes strong inductive biases. To overcome these limitations, we introduce Dynamic LENS, a modeling paradigm that combines the flexible uncertainty-preserving properties of variational autoencoders with the principled information integration of Bayesian state-space models. Dynamic LENS allows information from student responses to be collected across time, while treating responses from the same test as exchangeable observations generated by a shared latent state. It represents student knowledge as Gaussian distributions in high-dimensional space and combines estimates both within tests and across time using Bayesian updating. We show that Dynamic LENS has similar predictive performance to competing models, while preserving the epistemic uncertainty - the deep learning analogue to measurement error - that DKT models lack. This approach provides a conceptual bridge across an important divide between models designed for formative practice and summative assessment.