Retrieval-Augmented Generation (RAG): Architectures, Evaluation Metrics, and Security Challenges in Large Language Models

Abstract

Retrieval-Augmented Generation (RAG) is a sophisticated approach employed to enhance the efficiency of Large Language Models (LLMs). Most of the existing LLMs primarily rely on pre-trained data, which can be either obsolete or insufficient at times, hence providing suboptimal outcomes. To mitigate this problem, RAG begins by searching for relevant content and employs that content to produce a response. In this way, it becomes possible to yield better outputs. This paper provides insight into the concept of RAG through its architecture, working mechanism, and evaluation processes. It outlines various challenges associated with the technique, including sourcing quality data, delayed output, and security concerns. Furthermore, this study discusses current developments related to RAG and explores critical research gaps that can be addressed in the future.