A Retrieval-Augmented Large Language Model for Dynamic Personalization in Intelligent Tutoring Systems

Dynamic Retrieval Augmented Generation for Enterprise Knowledge Intelligence Systems using Large Language Models

To address the difficulty faced by university faculty and students in obtaining useful information from massive campus data, this paper proposes an intelligent campus question-and-answer (Q&A) system based on dynamic retrieval-augmented generation (RAG) technology, using campus administrative knowledge as the data source. The system integrates large language models (LLMs) with domain-specific professional knowledge, leveraging the Campus All-in-One project as a foundation. It constructs a campus knowledge base that includes administrative guides, frequently asked questions, and regulatory documents as an external data corpus. By applying the Infinity database, designed specifically for dynamic RAG applications, and employing prompt engineering, the model’s ability to generate accurate and context-aware answers is enhanced. Through this dynamic RAG-based approach tailored for the education domain, the system provides users with interactive access to a wide range of campus administrative information, helping to resolve common issues, simplify inquiry processes for teachers and students, and reduce the workload of campus management.

Combining RAG, LLMs, Vector Databases and Semantic Search in Intelligent Tutoring Systems

Artificial intelligence has improved greatly and its demand in the education field has increased. To satisfy this demand, this research paper proposes an intelligent tutoring system which uses artificial intelligence techniques like Retrieval-Augmented Generation and Large Language Models. It aims to provide context-relevant and personalized help to students in the learning process. The system has a 3-layer architecture. The frontend layer is managed by React for smooth user interaction. The backend layer is handled by FastAPI for proper processing and response generation and the database layer is managed by ChromaDB, a vector database, which handles proper document storage and data retrieval. Students can upload their study materials such as textbooks, notes, etc. in various formats like PDF, DOCX, TXT. Then, the system processes the documents by recursively splitting text and generating embeddings to convert unstructured content into a proper structured knowledge base. After this, Retrieval-Augmented Generation helps retrieve or fetch the most relevant embeddings and combine them with user’s queries to generate contextually correct answers, based on user upload documents. This helps reduce hallucinations, which is the main aim. The system can also automatically generate flashcards and quizzes with adjustable difficulty. To evaluate the system’s performance, different document-based queries were tried and the system had 90% accuracy on average with 20%-30% decrease in hallucination (as compared to other systems). The response time is between 2 to 5 seconds. These results show the benefits of combining Retrieval-Augmented Generation with LLMs.

A Framework for Adaptive Knowledge-Augmented Mizo Large Language Models Using Retrieval-Augmented Generation and Continual Learning

The deployment of Large Language Models (LLMs) for low-resource languages is challenging due to the lack of linguistic resources, sparse digital content and the absence of structured knowledge bases. In this paper, we present an adaptive knowledge-augmented framework for Mizo Large Language Models by combining Retrieval-Augmented Generation (RAG) with continual learning. This methodology harnesses semantic retrieval with dense embeddings and FAISS indexing, adaptive evidence re-ranking, parameter-efficient fine-tuning, and incremental knowledge updating to enhance factual accuracy and decrease hallucinations. Experimental evaluation shows better retrieval performance, greater text creation quality, and superior human evaluation scores than typical multilingual LLMs and static RAG methods. Moreover, the continual learning technique allows for effective integration of newly accessible Mizo resources, without re-training the model from scratch. The suggested architecture offers a scalable, stable and reusable method for the development of intelligent language technologies for Mizo and other low-resource languages.

Retrieval-Augmented Generation (Rag) Chatbots for Education

Retrieval-Augmented Generation (RAG) has emerged as a transformative approach for enhancing the capabilities of conversational artificial intelligence by integrating large language models with external knowledge retrieval mechanisms. In the educational domain, RAG-powered chatbots address limitations of traditional AI systems, such as factual inaccuracies, outdated knowledge, and hallucinated responses, by retrieving relevant information from trusted academic resources before generating answers. This chapter examines the principles, architecture, and applications of RAG chatbots in teaching, learning, and academic support. It discusses how these systems facilitate personalized learning, intelligent tutoring, automated question answering, curriculum assistance, and institutional support while improving response accuracy, transparency, and contextual relevance. The chapter also explores the technological components of RAG systems, including embedding models, vector databases, retrieval strategies, and large language models, alongside practical implementation considerations in e Retrieval-Augmented Generation (RAG), educational chatbots, artificial intelligence in education, large language models, intelligent tutoring systems, personalized learning, vector databases, learning analytics, conversational AI, educational technology.

LLM-Based Intelligent Tutoring Systems: A Survey

A GenAI-Based Adaptive Tutoring ana Intelligent Assessment Framework for Personalized Learning

EduMind is introduced, a unified tutoring and assessment platform designed around a dual-track evaluation model that demonstrates how assessment and tutoring can be unified into a seamless workflow, and remained operationally stable throughout all testing phases.