This article proposes a novel framework for intelligent decision support systems based on retrieval augmented generation models and knowledge graphs, in order to overcome the shortcomings of current approaches. Systems Like Mistral 7B, LLaMA-2, and others tend to fail at contextual understanding, transparency, and reasoning over many steps involving many domains. Our proposed architecture combines the strengths of generative models, enhanced by external knowledge retrieval, with structured, linked representations of domain knowledge. With this synergy, we show improvement in decision accuracy, reasoning transparency, and context relevance compared to using either technology alone. The structure has a flexible knowledge orchestration layer that optimizes information exchange between structured representations and generative capabilities. Research conducted on three areas, namely, financial services, healthcare management, and the supply chain has shown that our method performs particularly well when it comes to cross-domain reasoning and ambiguous queries. This study deepens our understanding of knowledge-enhancing artificial intelligence systems as well as offers a roadmap for a next-generation decision support system. The framework is designed to tackle some of the most challenging issues faced by enterprises in making decisions. In particular, it draws from both context and expertise to provide explainable recommendations.
Wang et al. (Fri,) studied this question.