mlsanityData to 14 Oct 2026

A Systematic Literature Review of Retrieval-Augmented Generation: Techniques, Metrics, and Challenges

arXiv 2508.06401 ↗First posted 8 Aug 2025cs.DL cs.AI cs.CLcited by 17

On the map: Retrieval-augmented generation → RAG pipeline design and evaluation

Abstract (arXiv)

This systematic review of the research literature on retrieval-augmented generation (RAG) provides a focused analysis of the most highly cited studies published between 2020 and May 2025. A total of 128 articles met our inclusion criteria. The records were retrieved from ACM Digital Library, IEEE Xplore, Scopus, ScienceDirect, and the Digital Bibliography and Library Project (DBLP). RAG couples a neural retriever with a generative language model, grounding output in up-to-date, non-parametric memory while retaining the semantic generalisation stored in model weights. Guided by the PRISMA 2020 framework, we (i) specify explicit inclusion and exclusion criteria based on citation count and research questions, (ii) catalogue datasets, architectures, and evaluation practices, and (iii) synthesise empirical evidence on the effectiveness and limitations of RAG. To mitigate citation-lag bias, we applied a lower citation-count threshold to papers published in 2025 so that emerging breakthroughs with naturally fewer citations were still captured. This review clarifies the current research landscape, highlights methodological gaps, and charts priority directions for future research.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 0 of its 716 references that are in the map. First posted on arXiv 8 Aug 2025.

Builds on

0 of 716 references.

No references here yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 16.

17 papers.

Sort:

By area:

  1. 2026TEMPO: A Realistic Multi-Domain Benchmark for Temporal Reasoning-Intensive Retrievalcited by 6
  2. 2025Knowing the Answer Isn't Enough: Fixing Reasoning Path Failures in LVLMscited by 5
  3. 2026LURE-RAG: Lightweight Utility-driven Reranking for Efficient RAGcited by 2
  4. 2026Decoding as Optimisation on the Probability Simplex: From Top-K to Top-P (Nucleus) to Best-of-K Samplerscited by 2
  5. 2026Evaluating Evidence Grounding Under User Pressure in Instruction-Tuned Language Modelscited by 1
  6. 2026Retrieval-Augmented Generation Must Move Beyond Factual Grounding to Represent Diverse Opinionscited by 1
  7. 2026Quantifying Retriever-Generator Alignment in RAG with Local Explanationscited by 0
  8. 2026Towards AI Evaluation in Domain-Specific RAG Systems: The AgriHubi Case Studycited by 0
  9. 2026Reducing Hallucinations in Complex Question Answering using Simple Graph-based Retrieval-Augmented Generation (long version)cited by 0
  10. 2026Security and Privacy in Retrieval-Augmented Generation: Architectures, Threats, Defenses, and Future Directions for Building Trustworthy Systemscited by 0
  11. 2026Embedding Inference Attackcited by 0
  12. 2026Retrieval-Augmented Large Language Models as Components of Cognitive Computing architecture for Regulatory Knowledge Managementcited by 0
5 more
  1. 2026CTRAG: An In-Context Retrieval-based Framework for Automated Compliance Checking using LLMscited by 0
  2. 2026FootprintRAG: Visual Analytics for Evidence Context Refinement in RAG-based Scientific Literature Explorationcited by 0
  3. 2026EvidenT: Building Trustworthy Enterprise Assistants through Evidence Groundedness and Traceabilitycited by 0
  4. 2026Potential for Enhanced Learning in Machine Learning Classes by Using Wiki LLM Indexingcited by 0
  5. 2026Analyzing performance of Retrieval Augmented Generation models for Question Answering Taskscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024On the Capacity of Citation Generation by Large Language Models
  2. 2025CiteFix: Enhancing RAG Accuracy Through Post-Processing Citation Correction
  3. 2025Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Survey
  4. 2025Retrieval-Augmented Generation in Industry: An Interview Study on Use Cases, Requirements, Challenges, and Evaluation
  5. 2025OmniBench-RAG: A Multi-Domain Evaluation Platform for Retrieval-Augmented Generation Tools
  6. 2024Deploying Large Language Models With Retrieval Augmented Generation
  7. 2024A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions
  8. 2026Beyond Relevance: On the Relationship Between Retrieval and RAG Information Coverage