Cognitive Structure Generation: From Educational Priors to Policy Optimization

2025-08-18

AI Summary

Cognitive structure modeling has long suffered from poor interpretability and difficulty in quantitative evaluation. To address this, we propose the Cognitive Structure Generation (CSG) framework—the first to integrate diffusion probabilistic models with hierarchical reinforcement learning. CSG first pretrains a Cognitive Structure Diffusion Probabilistic Model (CSDPM) guided by educational priors, then refines the generation policy using multi-granularity educational reward signals, enabling interpretable, dynamic cognitive evolution modeling beyond static knowledge representation. Evaluated on four real-world educational datasets, CSG significantly improves knowledge tracing (AUC +3.2%) and competency diagnosis (F1 +4.7%), demonstrating strong generalizability and educational utility. Our core contributions are: (i) the first generative modeling framework for dynamic cognitive structure inference; and (ii) a synergistic paradigm that jointly leverages domain-specific educational priors and data-driven policy optimization.

Technology Category

• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Machine Learning: Structured Learning
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• 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

Cognitive structure is a student's subjective organization of an objective knowledge system, reflected in the psychological construction of concepts and their relations. However, cognitive structure assessment remains a long-standing challenge in student modeling and psychometrics, persisting as a foundational yet largely unassessable concept in educational practice. This paper introduces a novel framework, Cognitive Structure Generation (CSG), in which we first pretrain a Cognitive Structure Diffusion Probabilistic Model (CSDPM) to generate students' cognitive structures from educational priors, and then further optimize its generative process as a policy with hierarchical reward signals via reinforcement learning to align with genuine cognitive development levels during students' learning processes. Experimental results on four popular real-world education datasets show that cognitive structures generated by CSG offer more comprehensive and effective representations for student modeling, substantially improving performance on KT and CD tasks while enhancing interpretability.

Problem

• Assessing cognitive structure in student modeling and psychometrics
• Generating cognitive structures from educational priors using CSDPM
• Optimizing cognitive structure generation via reinforcement learning

Innovation

• Pretrains Cognitive Structure Diffusion Probabilistic Model
• Optimizes generative process via reinforcement learning
• Aligns with genuine cognitive development levels