A Review of Retrieval-Augmented Generation for University-Specific Chatbot Systems

Abstract

The rapid advancement of Artificial Intelligence (AI) and Natural Language Processing (NLP) has made Large Language Models (LLMs) pivotal in educational question-answering systems, particularly for university admission chatbots [1]. However, LLMs face critical challenges such as generating hallucinations, relying on outdated knowledge, and having non-transparent reasoning processes [10]. To address this, Retrieval-Augmented Generation (RAG) has emerged as a promising solution, incorporating knowledge from external databases to enhance the accuracy and credibility of generated responses [10]. This paper reviews the architecture and application of RAG-powered chatbots (RAGBots) designed for specific university domains [1]. A key finding is that while RAG systems like URAG, SAMCares, and Infersity v1 demonstrate utility in providing intelligent access to university resources [1, 3, 4], datasets for such closed domains are still difficult to obtain and curate [2]. Furthermore, complex RAG implementations often involve high operational costs and specialized modules [1]. The work highlights enhancements like Multi-Query and Ensemble Retrieval [6] and discusses critical challenges such as Document-Level Retrieval Mismatch (DRM) [8], concluding with a vision for reliable, domain-specific RAGBots in higher education.