Retrieval-Augmented Generation for Large Language Models: A Survey

  • 类型：arxiv
  • 标识：2312.10997
  • 链接：https://arxiv.org/abs/2312.10997
  • 主题：multimodal
  • 主分类：rag
  • 形态：survey
  • 被引：3933
  • 被引来源：Semantic Scholar
  • S2被引：3933
  • OpenAlex被引：705
  • 影响力被引：247
  • TLDR：This comprehensive review paper offers a detailed examination of the progression of RAG paradigms, encompassing the Naive RAG, the Advanced RAG, and the Modular RAG, and meticulously scrutinizes the tripartite foundation of RAG frameworks, which includes the retrieval, the generation and the augmentation techniques.
  • OpenAlex ID：W4389984066
  • OpenAlex DOI：10.48550/arxiv.2312.10997
  • DOI：10.48550/arxiv.2312.10997
  • DOI来源：OpenAlex
  • 开放获取：green
  • 开放获取链接：https://arxiv.org/pdf/2312.10997
  • OpenAlex更新：2026-08-23
  • 待LLM分类：否
  • 标题中文：Retrieval-Augmented Generation for Large Language Models: A Survey
  • TLDR中文：该综述细致梳理了 RAG 范式的演进，涵盖 Naive RAG、Advanced RAG 与 Modular RAG，并对 RAG 框架的三大基础支柱——检索、生成与增强技术——进行了深入审视。
  • 来源文件：
  • [OpenAlex discover]
  • [OpenAlex backfill]
  • [S2 enrich]