A Developmentally-Staged Transformer Framework for Progressive Cognitive Learning in Language Understanding
Open Access
- 12 November 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive and Developmental Systems
- Vol. PP (23798920) , 1-16
Abstract
Human language understanding develops progressively through stages of cognitive maturation, characterized by increasing memory capacity, attentional control, and abstraction. Inspired by this trajectory, we propose the Developmentally-Staged Transformer for Progressive Cognitive Learning (DST-PCL), a novel framework that models language understanding through staged architectural and functional growth. DST-PCL simulates cognitive development by incrementally expanding Transformer depth, input memory span, and attention complexity across a curriculum-aligned training schedule. Each stage activates a subset of model layers and imposes entropy-regularized attention constraints to reflect bounded human focus. A readiness-based transition controller governs stage advancement based on validation accuracy and attention sharpness. Theoretical analyses guarantee hypothesis class expansion, bounded generalization error, and stability under stage transitions. Empirical evaluations across three benchmark datasets BoolQ, MultiNLI, and ReClor demonstrate consistent gains over strong baselines, with up to +5.1% accuracy and +6.3 F1 improvement. Further, attention entropy and interpretability metrics confirm the cognitively plausible progression of model behavior. DST-PCL offers a new paradigm for cognitively grounded NLP systems that unify performance, developmental structure, and interpretability.Keywords
This publication has 26 references indexed in Scilit:
- SpikingResformer: Bridging ResNet and Vision Transformer in Spiking Neural Networks2024
- Concept-cognitive learning survey: Mining and fusing knowledge from dataInformation Fusion, 2024
- The impact of school support for professional development on teachers' adoption of student-centered pedagogy, students’ cognitive learning and abilities: A three-level analysisComputers & Education, 2024
- The implementation of the cognitive theory of multimedia learning in the design and evaluation of an AI educational video assistant utilizing large language modelsHeliyon, 2024
- ChatGPT effects on cognitive skills of undergraduate students: Receiving instant responses from AI-based conversational large language models (LLMs)Computers and Education: Artificial Intelligence, 2023
- Improving deep learning with prior knowledge and cognitive models: A survey on enhancing explainability, adversarial robustness and zero-shot learningCognitive Systems Research, 2023
- Modeling Multiple Language Learning in a Developmental Cognitive ArchitectureIEEE Transactions on Cognitive and Developmental Systems, 2020
- Measuring the Cognitive Complexity in the Comprehension of Modular Process ModelsIEEE Transactions on Cognitive and Developmental Systems, 2020
- Quantifying the Role of Vocabulary Knowledge in Predicting Future Word LearningIEEE Transactions on Cognitive and Developmental Systems, 2019
- Self-Supervised Vision-Based Detection of the Active Speaker as Support for Socially Aware Language AcquisitionIEEE Transactions on Cognitive and Developmental Systems, 2019