A systematic review of optimized retrieval-augmented generation frameworks for reducing hallucinations in large language models
Abstract
Large Language Models (LLMs) have proven to be making great progress on natural language processing, but they tend to produce hallucinated or even inaccurate information. The systematic review is focused on optimized Retrieval-Augmented Generation (RAG) frameworks and how they enhance the reliability and factual truth of the outputs of LLM. The paper examines the architecture of the RAG systems, retrieval methods, and optimization methods like embedding tuning, query expansion, and reranking. It also surveys methods of evaluation by such metrics as factual consistency and faithfulness. The results show that the incorporation of outside knowledge recall massively decreases hallucinations and improves the grounding in context. Although there are difficulties that are associated with scalability and knowledge management, optimized RAG frameworks present a good pathway towards creating trustworthy and evidence-based generative AI systems.
Keywords: Large Language Models; Retrieval-Augmented Generation; Hallucination Reduction; AI Reliability.
How strong is the evidence?
Evidence Hub reads this as a systematic review. Its evidence level is 1 of 5 (Highest · pooled evidence). Pooled evidence from several studies sits at the top of the evidence pyramid.
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.