RAG-PRISM: A Personalized, Rapid, and Immersive Skill Mastery Framework with Adaptive Retrieval-Augmented Tutoring

2025-08-30

AI Summary

The Fourth Industrial Revolution (4IR) accelerates digital transformation, exacerbating STEM skill gaps among aging workers and necessitating scalable, personalized reskilling solutions. To address this, we propose an adaptive pedagogical framework integrating generative AI with retrieval-augmented generation (RAG), featuring a novel dual-mode tutoring mechanism that concurrently delivers personalized topic recommendations and context-aware content generation. Learning paths are dynamically optimized using document hit rate and mean reciprocal rank (MRR). The framework leverages GPT-3.5/GPT-4, a synthetically generated QA dataset, and a human-annotated benchmark. Evaluated in 4IR cybersecurity education, GPT-4–generated content achieves 87% relevance and 100% alignment—substantially outperforming conventional manual query methods. Our approach enables scalable, low-cost, high-fidelity, end-to-end reskilling.

Technology Category

• Humans and AI: AI for Accessibility
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Machine Learning: Multimodal Learning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

The rapid digital transformation of Fourth Industrial Revolution (4IR) systems is reshaping workforce needs, widening skill gaps, especially for older workers. With growing emphasis on STEM skills such as robotics, automation, artificial intelligence (AI), and security, large-scale re-skilling and up-skilling are required. Training programs must address diverse backgrounds, learning styles, and motivations to improve persistence and success, while ensuring rapid, cost-effective workforce development through experiential learning. To meet these challenges, we present an adaptive tutoring framework that combines generative AI with Retrieval-Augmented Generation (RAG) to deliver personalized training. The framework leverages document hit rate and Mean Reciprocal Rank (MRR) to optimize content for each learner, and is benchmarked against human-generated training for alignment and relevance. We demonstrate the framework in 4IR cybersecurity learning by creating a synthetic QA dataset emulating trainee behavior, while RAG is tuned on curated cybersecurity materials. Evaluation compares its generated training with manually curated queries representing realistic student interactions. Responses are produced using large language models (LLMs) including GPT-3.5 and GPT-4, assessed for faithfulness and content alignment. GPT-4 achieves the best performance with 87% relevancy and 100% alignment. Results show this dual-mode approach enables the adaptive tutor to act as both a personalized topic recommender and content generator, offering a scalable solution for rapid, tailored learning in 4IR education and workforce development.

Problem

• Addressing widening skill gaps for older workers in digital transformation
• Providing personalized adaptive tutoring for diverse learner backgrounds
• Ensuring rapid cost-effective workforce development through experiential learning

Innovation

• Combines generative AI with retrieval-augmented generation
• Uses document hit rate and MRR for optimization
• Employs dual-mode as recommender and content generator