Improving Retrieval-Augmented Generation: A Systematic Literature Review of Retrieval-Enhancement Techniques
Abstract
Abstract Large language models are highly fluent and effective across a wide range of tasks but remain vulnerable to hallucination, knowledge staleness, and limited provenance of generated outputs. Retrieval-augmented generation addresses these limitations by grounding generation in externally retrieved evidence and has become a rapidly growing research area. However, advances are dispersed across pipeline stages, evaluated using heterogeneous metrics, and spread across multiple research communities, leaving the field without a comprehensive synthesis. This paper presents a systematic literature review of 173 studies on RAG retrieval enhancement published between 2024 and 2026, identified through searches across six major bibliographic databases. Studies are categorised by (i) their primary technical contribution, (ii) application domain, and (iii) the RAG pipeline stage they target, including pre-retrieval, retrieval, post-retrieval, generation-integrated approaches, and cross-stage modular or agentic architectures. Representative and highly cited methods are analysed in detail while ensuring coverage of all included studies. The review identifies four key findings: Uneven research effort across pipeline stages, fragmented evaluation practices, limited reporting of computational cost, and a strong focus on healthcare applications. Based on these findings, it proposes a structured research agenda to advance RAG systems toward more comparable, efficient, and generalisable…
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.