TLSQKT: A Question-Aware Dual-Channel Transformer for Literacy Tracing from Learning Sequences

TL;DR

This paper introduces TLSQKT, a novel Transformer-based model for Literacy Tracing that models higher-order cognitive abilities from learning sequences, outperforming traditional knowledge tracing models and providing interpretable literacy development insights.

Contribution

The paper redefines knowledge tracing as Literacy Tracing and proposes TLSQKT, a dual-channel Transformer model that captures long-range dependencies and jointly encodes responses and item semantics.

Findings

TLSQKT outperforms baseline models on literacy metrics.

The model reveals interpretable literacy development trajectories.

Transfer learning shows signals can be used with limited literacy labels.

Abstract

Knowledge tracing (KT) supports personalized learning by modeling how students' knowledge states evolve over time. However, most KT models emphasize mastery of discrete knowledge components, limiting their ability to characterize broader literacy development. We reframe the task as Literacy Tracing (LT), which models the growth of higher-order cognitive abilities and literacy from learners' interaction sequences, and we instantiate this paradigm with a Transformer-based model, TLSQKT (Transformer for Learning Sequences with Question-Aware Knowledge Tracing). TLSQKT employs a dual-channel design that jointly encodes student responses and item semantics, while question-aware interaction and self-attention capture long-range dependencies in learners' evolving states. Experiments on three real-world datasets - one public benchmark, one private knowledge-component dataset, and one private literacy dataset - show that TLSQKT consistently outperforms strong KT baselines on literacy-oriented metrics and reveals interpretable developmental trajectories of learners' literacy. Transfer experiments further indicate that knowledge-tracing signals can be leveraged for literacy tracing, offering a practical route when dedicated literacy labels are limited. These findings position literacy tracing as a scalable component of intelligent educational systems and lay the groundwork for literacy evaluation in future large-scale educational models.