RAG 沿革

论文

代表论文

每项技术只收推动它的论文，不收综述之外的二手解读。关系图覆盖下面的全部论文，节点打开原文，技术名回到站内短文。

论文之间的关系

从左到右是年份，同一年里按技术环节从上到下排列。移到论文上，会突出直接相关的工作。

  • 演进
  • 组合
  • 针对局限
RAG 论文关系图全部收录论文按发表年份从左向右排列。实线表示演进，虚线表示组合，点线表示针对前一篇工作的局限。Reciprocal Rank Fusion Outperforms Condorcet and Individual Rank Learning Methods，2009，Gordon V. Cormack, Charles L. A. Clarke, Stefan Buettcher倒数排名融合检索The Probabilistic Relevance Framework: BM25 and Beyond，2009，Stephen Robertson, Hugo ZaragozaBM25检索Passage Re-ranking with BERT，2019，Rodrigo Nogueira, Kyunghyun Cho重排序检索Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks，2020，Patrick Lewis et al.朴素 RAGLewisREALM: Retrieval-Augmented Language Model Pre-Training，2020，Kelvin Guu et al.REALM架构Dense Passage Retrieval for Open-Domain Question Answering，2020，Vladimir Karpukhin et al.稠密检索检索Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval，2020，Wenhan Xiong et al.多跳检索检索ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT，2020，Omar Khattab, Matei Zaharia后期交互检索Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering，2020，Gautier Izacard, Edouard GraveFusion-in-Decoder生成Generalization through Memorization: Nearest Neighbor Language Models，2020，Urvashi Khandelwal, Omer Levy, Dan Jurafsky, Luke Zettlemoyer, Mike LewiskNN-LM生成On Faithfulness and Factuality in Abstractive Summarization，2020，Joshua Maynez, Shashi Narayan, Bernd Bohnet, Ryan McDonald忠实度评估Improving Language Models by Retrieving from Trillions of Tokens，2021，Sebastian Borgeaud et al.RETRO架构WebGPT: Browser-assisted Question-answering with Human Feedback，2021，Reiichiro Nakano et al.WebGPT编排Atlas: Few-shot Learning with Retrieval Augmented Language Models，2022，Gautier Izacard et al.Atlas架构MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text，2022，Wenhu Chen et al.多模态 RAG索引Precise Zero-Shot Dense Retrieval without Relevance Labels，2022，Luyu Gao, Xueguang Ma, Jimmy Lin, Jamie CallanHyDE查询An Analysis of Fusion Functions for Hybrid Retrieval，2022，Sebastian Bruch, Siyu Gai, Amir Ingber混合检索检索Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions，2022，Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, Ashish Sabharwal迭代检索IrcotDemonstrate-Search-Predict: Composing Retrieval and Language Models for Knowledge-intensive NLP，2022，Omar Khattab et al.Demonstrate-Search-Predict编排Retrieval-Augmented Generation for Large Language Models: A Survey，2023，Yunfan Gao et al.朴素 RAG综述RA-DIT: Retrieval-Augmented Dual Instruction Tuning，2023，Xi Victoria Lin et al.RA-DIT架构Query Rewriting for Retrieval-Augmented Large Language Models，2023，Xinbei Ma, Yeyun Gong, Pengcheng He, Hai Zhao, Nan Duan查询改写查询Query2doc: Query Expansion with Large Language Models，2023，Liang Wang, Nan Yang, Furu Wei多查询查询LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression，2023，Huiqiang Jiang et al.上下文压缩LongLLMLinguaRECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation，2023，Fangyuan Xu, Weijia Shi, Eunsol Choi上下文压缩RECOMPEnabling Large Language Models to Generate Text with Citations，2023，Tianyu Gao, Howard Yen, Jiatong Yu, Danqi Chen引用归因生成Lost in the Middle: How Language Models Use Long Contexts，2023，Nelson F. Liu et al.中间迷失生成REPLUG: Retrieval-Augmented Black-Box Language Models，2023，Weijia Shi et al.REPLUGREPLUGSelf-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection，2023，Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, Hannaneh HajishirziSelf-RAG生成Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy，2023，Zhihong Shao et al.迭代检索Iter-RetgenActive Retrieval Augmented Generation，2023，Zhengbao Jiang et al.FLARE编排ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems，2023，Jon Saad-Falcon et al.ARES评估Benchmarking Large Language Models in Retrieval-Augmented Generation，2023，Jiawei Chen et al.RGB 基准评估FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation，2023，Tu Vu et al.新鲜度工程Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Models，2024，Michael Günther et al.切块策略索引Contextual Retrieval，2024，Anthropic上下文检索索引ColPali: Efficient Document Retrieval with Vision Language Models，2024，Manuel Faysse et al.ColPali索引From Local to Global: A Graph RAG Approach to Query-Focused Summarization，2024，Darren Edge et al.GraphRAGFrom Local to GlobalLightRAG: Simple and Fast Retrieval-Augmented Generation，2024，Zirui Guo, Lianghao Xia, Yanhua Yu, Tu Ao, Chao HuangLightRAG索引LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs，2024，Ziyan Jiang, Xueguang Ma, Wenhu ChenLongRAG索引RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval，2024，Parth Sarthi et al.RAPTOR索引Corrective Retrieval Augmented Generation，2024，Shi-Qi Yan, Jia-Chen Gu, Yun Zhu, Zhen-Hua LingCRAG检索HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models，2024，Bernal Jiménez Gutiérrez, Yiheng Shu, Yu Gu, Michihiro Yasunaga, Yu SuHippoRAG检索RAFT: Adapting Language Model to Domain Specific RAG，2024，Tianjun Zhang et al.RAFT生成RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs，2024，Yue Yu, Wei Ping et al.RankRAG生成FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research，2024，Jiajie Jin et al.REPLUGFlashRAGSpeculative RAG: Enhancing Retrieval Augmented Generation through Drafting，2024，Zilong Wang, Zifeng Wang et al.Speculative RAG生成Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity，2024，Soyeong Jeong et al.Adaptive-RAG编排CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models，2024，Yuanjie Lyu et al.CRUD-RAG评估RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models，2024，Cheng Niu et al.RAGTruth评估The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)，2024，Shenglai Zeng et al.权限与隐私安全PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models，2024，Wei Zou et al.知识库投毒安全RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation，2024，Chao Jin et al.检索缓存工程Retrieval-Augmented Generation with Graphs (GraphRAG)，2025，Haoyu Han et al.GraphRAGGraphRAGA Survey of Multimodal Retrieval-Augmented Generation，2025，Lang Mei, Siyu Mo, Zhihan Yang, Chong Chen多模态检索规划编排Introducing deep research，2025，OpenAI深度研究编排Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs，2025，Yangning Li, Weizhi Zhang et al.推理与检索协同编排Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG，2025，Aditi Singh, Abul Ehtesham, Saket Kumar, Tala Talaei Khoei, Athanasios V. VasilakosAgentic RAG编排When to Use Graphs in RAG: A Comprehensive Analysis for Graph Retrieval-Augmented Generation，2025，Zhishang Xiang, Chuanjie Wu, Qinggang Zhang et al.GraphRAG 适用边界评估Rethinking Knowledge Retrieval for Generation: A Survey on RAG Architectures and Applications，2026，Meghana Sunil, Shravya V, Shravan Venkatraman, Joe Dhanith P R四条轴线架构RAGRouter-Bench: A Dataset and Benchmark for Adaptive RAG Routing，2026，Ziqi Wang, Xi Zhu, Shuhang Lin, Haochen Xue, Minghao Guo, Yongfeng Zhang检索路由编排Legal RAG Bench: An End-to-End Benchmark for Legal RAG，2026，Abdur-Rahman Butler, Umar Butler领域评测Legal RAG BenchMRAG: Benchmarking Retrieval-Augmented Generation for Bio-medicine，2026，Wei Zhu领域评测MRAGLIT-RAGBench: Benchmarking Generator Capabilities of Large Language Models in Retrieval-Augmented Generation，2026，Koki Itai, Shunichi Hasegawa, Yuta Yamamoto, Gouki Minegishi, Masaki Otsuki生成器能力评测评估RAGPerf: An End-to-End Benchmarking Framework for Retrieval-Augmented Generation Systems，2026，Shaobo Li et al.系统性能基准工程

节点覆盖目前收录的全部论文，打开后进入原文。连线只表示编辑过的直接关系。

2026

2025

2024

2023

2022

2021

2020

2019

Passage Re-ranking with BERT

Rodrigo Nogueira, Kyunghyun Cho

用 BERT 交叉编码器给已经召回的段落重新打分，是神经重排序进入检索系统的常用起点。

重排序

2009