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

TL;DR

This paper targets the gap between traditional Knowledge Tracing (KT) and broader literacy development by introducing Literacy Tracing (LT) and a Transformer-based model, TLSQKT, that jointly encodes student responses and item semantics through dual channels with question-aware interaction. TLSQKT uses three parallel streams (Question, Ability, Application) with LSTM and Transformer components to produce $\alpha_t$, $\beta_t$, and $\gamma_{t+1}$, which are linearly combined to predict $\hat{r}_{t+1}$. Experiments on three real-world datasets show TLSQKT outperforms strong KT baselines on literacy-oriented metrics and yields interpretable literacy trajectories; transfer experiments demonstrate that knowledge-tracing signals can support LT when explicit literacy labels are scarce. The work suggests LT can be scaled within intelligent educational systems and lays groundwork for literacy evaluation in future large-scale educational models.

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.

Figures (2)

• Figure 1: Overview of the proposed Transformer for Learning Sequences with Question-Aware Knowledge Tracing model.
• Figure 2: Results of ablation experiments on all three datasets.