mlsanityData to 14 Oct 2026

FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAG

arXiv 2410.10293 ↗First posted 14 Oct 2024cs.IR cs.CLcited by 18

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

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) prevails in Large Language Models. It mainly consists of retrieval and generation. The retrieval modules (a.k.a. retrievers) aim to find useful information used to facilitate the generation modules (a.k.a. generators). As such, generators' performance largely depends on the effectiveness and efficiency of retrievers. However, the widely used retrieval paradigm remains flat. It treats retrieval procedures as a one-off deal with constant granularity. Despite effectiveness, we argue that they suffer from two limitations: (1) flat retrieval exerts a significant burden on one retriever; (2) constant granularity limits the ceiling of retrieval performance. In this work, we propose a progressive retrieval paradigm with coarse-to-fine granularity for RAG, termed FunnelRAG, so as to balance effectiveness and efficiency. Specifically, FunnelRAG establishes a progressive retrieval pipeline by collaborating coarse-to-fine granularity, large-to-small quantity, and low-to-high capacity, which can relieve the burden on one retriever and also promote the ceiling of retrieval performance. Extensive experiments manifest that FunnelRAG achieves comparable retrieval performance while the time overhead is reduced by nearly 40 percent.

Key facts. Cited by 18 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 35 of its 59 references that are in the map. First posted on arXiv 14 Oct 2024.

Builds on

35 of 59 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs21 Jun
  2. 2024Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers22 Mar

Other references · 33

  1. 2017Attention Is All You Needcited by 60,361
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  5. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  6. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  7. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  8. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  9. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  10. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  11. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
  12. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
21 more
  1. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,073
  2. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
  3. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 849
  4. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 792
  5. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 695
  6. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 573
  7. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 451
  8. 2020Document Ranking with a Pretrained Sequence-to-Sequence Modelcited by 376
  9. 2020Distilling Knowledge from Reader to Retriever for Question Answeringcited by 226
  10. 2023RA-DIT: Retrieval-Augmented Dual Instruction Tuningcited by 195
  11. 2020Funnel-Transformer: Filtering out Sequential Redundancy for Efficient Language Processingcited by 162
  12. 2024xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Tokencited by 125
  13. 2022RankT5: Fine-Tuning T5 for Text Ranking with Ranking Lossescited by 115
  14. 2024BM25S: Orders of magnitude faster lexical search via eager sparse scoringcited by 88
  15. 2023Augmentation-Adapted Retriever Improves Generalization of Language Models as Generic Plug-Incited by 71
  16. 2019Knowledge Guided Text Retrieval and Reading for Open Domain Question Answeringcited by 59
  17. 2022Tevatron: An Efficient and Flexible Toolkit for Dense Retrievalcited by 47
  18. 2020COLD: Towards the Next Generation of Pre-Ranking Systemcited by 31
  19. 2024CrAM: Credibility-Aware Attention Modification in LLMs for Combating Misinformation in RAGcited by 22
  20. 2024Retrieval Augmented End-to-End Spoken Dialog Modelscited by 20
  21. 2024Retrieval Augmented Generation in Prompt-based Text-to-Speech Synthesis with Context-Aware Contrastive Language-Audio Pretrainingcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 9; 2026: 5.

18 papers.

Sort:

By area:

  1. 2024ZoomEye: Enhancing Multimodal LLMs with Human-Like Zooming Capabilities through Tree-Based Image Explorationcited by 103
  2. 2025KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Modelcited by 36
  3. 2025APT: Improving Specialist LLM Performance with Weakness Case Acquisition and Iterative Preference Trainingcited by 12
  4. 2026LMEB: Long-horizon Memory Embedding Benchmarkcited by 7
  5. 2024ImageRAG: Enhancing Ultra High Resolution Remote Sensing Imagery Analysis with ImageRAGcited by 6
  6. 2026Courtroom-Style Multi-Agent Debate with Progressive RAG and Role-Switching for Controversial Claim Verificationcited by 4
  7. 2024How Does Knowledge Selection Help Retrieval Augmented Generation?cited by 3
  8. 2024RaSeRec: Retrieval-Augmented Sequential Recommendationcited by 3
  9. 2025Revisiting Funnel Transformers for Modern LLM Architectures with Comprehensive Ablations in Training and Inference Configurationscited by 3
  10. 2025On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Surveycited by 3
  11. 2026Bi-Mem: Bidirectional Construction of Hierarchical Memory for Personalized LLMs via Inductive-Reflective Agentscited by 3
  12. 2025SR-KI: Scalable and Real-Time Knowledge Integration into LLMs via Supervised Attentioncited by 2
6 more
  1. 2025Learning to Extract Rational Evidence via Reinforcement Learning for Retrieval-Augmented Generationcited by 1
  2. 2025Path Pooling: Training-Free Structure Enhancement for Efficient Knowledge Graph Retrieval-Augmented Generationcited by 0
  3. 2025SeaPO: Strategic Error Amplification for Robust Preference Optimization of Large Language Modelscited by 0
  4. 2025Skim-Aware Contrastive Learning for Efficient Document Representationcited by 0
  5. 2026Reason Before You Retrieve: Agentic Planning for Multi-modal RAGcited by 0
  6. 2026LifeFuse-Mem: Lifecycle-Aware State Fusion Against Temporary Overwriting for Long-Term Memorycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024XRAG: eXamining the Core -- Benchmarking Foundational Components in Advanced Retrieval-Augmented Generation
  2. 2026Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning
  3. 2024Toward Optimal Search and Retrieval for RAG
  4. 2026Revisiting RAG Retrievers: An Information Theoretic Benchmark
  5. 2024CoFE-RAG: A Comprehensive Full-chain Evaluation Framework for Retrieval-Augmented Generation with Enhanced Data Diversity
  6. 2025FedRAG: A Framework for Fine-Tuning Retrieval-Augmented Generation Systems
  7. 2025When Retrieval Succeeds and Fails: Rethinking Retrieval-Augmented Generation for LLMs
  8. 2024FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research