A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models

By Wenqi Fan, Yujuan Ding, Liang-bo Ning, Shijie Wang, Hengyun Li, Dawei Yin, Tat-Seng Chua, Qing Li. Knowledge Discovery and Data Mining, 2024

994 citations recorded by the source corpus.

As one of the most advanced techniques in AI, Retrieval-Augmented Generation (RAG) can offer reliable and up-to-date external knowledge, providing huge convenience for numerous tasks. Particularly in the era of AI-Generated Content (AIGC), the powerful capacity of retrieval in providing additional knowledge enables RAG to assist existing generative AI in producing high-quality outputs. Recently, Large Language Models (LLMs) have demonstrated revolutionary abilities in language understanding and generation, while still facing inherent limitations such as hallucinations and out-of-date internal knowledge. Given the powerful abilities of RAG in providing the latest and helpful auxiliary information, Retrieval-Augmented Large Language Models (RA-LLMs) have emerged to harness external and authoritative knowledge bases, rather than solely relying on the model's internal knowledge, to augment the quality of the generated content of LLMs. In this survey, we comprehensively review existing research studies in RA-LLMs, covering three primary technical perspectives: Furthermore, to deliver deeper insights, we discuss current limitations and several promising directions for future research. Updated information about this survey can be found at: https://advanced-recommender-systems.github.io/RAG-Meets-LLMs/

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/eb9c4a07a336e8deefe7b399c550d3af0241238e

Citations in the corpus

• LightRAG: Simple and Fast Retrieval-Augmented Generation (2024, neutral): “As large language models (LLMs) evolve, researchers aim to enhance their ability to interpret graph-structured data.”
• Temporal Preference Optimization for Unsupervised Retrieval (2026, unknown): “Copyright 2026 by the author(s). systems (Bobadilla et al., 2013; Zhang et al., 2019; Singh, 2023; Li et al., 2024), question answering (Karpukhin et al., 2020; Zhang et al., 2023a;b), and retrieval-augmented generation (Lewis et al., 2020; Zhao et al., 2024a; Fan et al., 2024; Kwon et al., 2025).”
• A Matryoshka Hierarchical RAG for Efficient Multi-Hop Question Answering (2026, unknown): “A dense similarity between a query and a single document cannot capture chains of reasoning that span multiple documents, and flat indices do not exploit the hierarchical semantic structure of the corpus [5].”
• An Empirical Study of Knowledge Graph-Enhanced RAG for Information Security Compliance (2026, unknown): “Comprehensive surveys by Gao et al. [9] and Fan et al. [10] provide extensive taxonomies of RAG architectures and identify retrieval quality as a critical bottleneck.”
• Changing the Optics: Comparing Traditional and Retrieval-Augmented GenAI E-Tutorials in Interdisciplinary Learning (2026, unknown): “Because integration of retrieved information into the input layer is a simple and common way to provide additional context to the generator [25], retrieved information, the user query, and the user chat history were combined and provided as input to the large language model in our implementation…”
• ResearchGPT: Benchmarking and Training LLMs for End-to-End Computer Science Research Workflows (2025, unknown): “Each paper is converted from PDF format into Markdown using the MinerU (Wang et al., 2024; He et al., 2024) toolkit.”
• LLM-Enhanced Semantic Text Segmentation (2025, unknown): “This question is particularly relevant for retrieval-augmented generation (RAG) systems [12,13], where the quality of retrieved evidence depends critically on how textual data is partitioned into coherent units.”
• Retrieval And Structuring Augmented Generation with Large Language Models (2025, unknown): “It plays a crucial role in various tasks including internet browsing [115, 122, 201], question-answering systems [1, 111, 238], and LLM applications [53, 64, 303].”
• ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation (2025, unknown): “To enhance the trustworthiness and interpretability of LLMs, Retrieval-Augmented Generation (RAG) methods [15, 16, 24, 26, 71, 77, 80] have emerged as a core approach, which often retrieve relevant information from documents, relational data, and graph data to facilitate the QA tasks.”