Answers are grounded in this paper and cite their sources.
Retrieval-Augmented Generation (RAG) has emerged as an important approach for enhancing the capabilities of Generative Artificial Intelligence in enterprise environments. By combining information retrieval with Large Language Models (LLMs), RAG enables organizations to connect generative AI with current, domain-specific, and proprietary knowledge. This article examines RAG from an interdisciplinary perspective, integrating concepts from Computer Science, Commerce, Management, and Business Analytics. It discusses the conceptual foundations and architecture of RAG and examines its applications in knowledge management, customer service, human resource management, finance, marketing, business analytics, and decision support. The article further identifies key business benefits, including improved knowledge accessibility, productivity, response relevance, and managerial support, while examining challenges related to data quality, retrieval accuracy, hallucination, privacy, security, governance, and human oversight. The study also highlights the potential of RAG to support evidence-based enterprise decisionmaking and proposes a conceptual framework linking RAG capabilities, enterprise applications, business benefits, decision support, and organizational outcomes. The article concludes by identifying future research opportunities in secure, explainable, multimodal, domain-specific, and agentic RAG systems.
No takes yet. Share an insight, caveat, or question.
ANANDAPRIYA et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: