Live Knowledge Tracing: Real-Time Adaptation using Tabular Foundation Models

TL;DR

This paper introduces a real-time knowledge tracing method using tabular foundation models that aligns sequences at inference time, enabling online adaptation and significantly faster predictions without traditional training.

Contribution

It presents a novel paradigm leveraging TFMs for live knowledge tracing, eliminating offline training and enabling online, in-context learning for student modeling.

Findings

Achieves up to 53x speedups over traditional models.

Maintains competitive predictive performance across multiple datasets.

Enables real-time adaptation in student learning scenarios.

Abstract

Deep knowledge tracing models have achieved significant breakthroughs in modeling student learning trajectories. However, these architectures require substantial training time and are prone to overfitting on datasets with short sequences. In this paper, we explore a new paradigm for knowledge tracing by leveraging tabular foundation models (TFMs). Unlike traditional methods that require offline training on a fixed training set, our approach performs real-time ''live'' knowledge tracing in an online way via in-context learning. TFMs align testing sequences with relevant training sequences at inference time, therefore skipping the training step entirely. We demonstrate, using several datasets of increasing size, that our method achieves competitive predictive performance with up to 53x speedups on average, in a setting where student interactions are observed progressively over time.