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

2025-10-25

AI Summary

This work addresses the limitation of conventional knowledge tracing (KT) in modeling higher-order competency development, and formally introduces the novel task of literacy tracing (LT), instantiated through literacy-specific tracing. To this end, we propose TLSQKT, a dual-channel Transformer architecture that jointly models student response sequences and item semantics, incorporating a question-aware self-attention mechanism to explicitly capture long-term cognitive evolution and yield interpretable developmental trajectories. Our approach integrates sequential modeling, semantic encoding, and transfer learning, demonstrating effective migration of knowledge-level signals to competency-oriented modeling. Evaluated on three real-world educational datasets, TLSQKT significantly outperforms state-of-the-art KT baselines, particularly on literacy-aligned metrics. This work establishes a new paradigm for large-scale, competency-aware educational assessment and provides a technically viable pathway toward operationalizing literacy tracking in intelligent educational systems.

Technology Category

• Natural Language Processing: Question Answering
• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Intelligent Query Processing

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

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.

Problem

• Modeling higher-order cognitive abilities from learning sequences
• Capturing literacy development beyond discrete knowledge components
• Leveraging knowledge tracing signals for literacy evaluation

Innovation

• Dual-channel design encodes responses and semantics
• Question-aware attention captures long-range dependencies
• Transformer architecture models literacy development trajectories