|
As digital education transitions from static content delivery to dynamic interaction, AI-based pedagogical models have emerged as the primary drivers of student engagement. This study evaluates the efficacy of AI-driven personalization specifically Large Language Models (LLMs) and Adaptive Learning Systems (ALS) within higher education digital environments. Using a mixed-methods approach, we analyze student performance metrics and engagement levels across two groups (N=20). Results indicate a 15% increase in retention rates and a significant reduction in learning fatigue among students using AI-integrated paths. However, the study also highlights the necessity of “Human-in-the-Loop” (HITL) oversight to mitigate algorithmic bias. We conclude that while AI models significantly enhance personalized pacing, they must be integrated as pedagogical assistants rather than primary instructors.
|