mlsanityData to 7 Oct 2026

Hierarchical Document Refinement for Long-context Retrieval-augmented Generation

arXiv 2505.10413 ↗First posted 15 May 2025cs.CLcited by 16

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

Abstract (arXiv)

Real-world RAG applications often encounter long-context input scenarios, where redundant information and noise results in higher inference costs and reduced performance. To address these challenges, we propose LongRefiner, an efficient plug-and-play refiner that leverages the inherent structural characteristics of long documents. LongRefiner employs dual-level query analysis, hierarchical document structuring, and adaptive refinement through multi-task learning on a single foundation model. Experiments on seven QA datasets demonstrate that LongRefiner achieves competitive performance in various scenarios while using 10x fewer computational costs and latency compared to the best baseline. Further analysis validates that LongRefiner is scalable, efficient, and effective, providing practical insights for real-world long-text RAG applications. Our code is available at https://github.com/ignorejjj/LongRefiner.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 42 of its 61 references that are in the map. First posted on arXiv 15 May 2025.

Builds on

42 of 61 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025More Documents, Same Length: Isolating the Challenge of Multiple Documents in RAG6 Mar
  2. 2024LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs21 Jun
  3. 2024FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research22 May
  4. 2023Retrieval-Augmented Generation for Large Language Models: A Survey18 Dec

Other references · 38

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  4. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  6. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  7. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  8. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  9. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  10. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  11. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,103
  12. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 571
26 more
  1. 2019ELI5: Long Form Question Answeringcited by 567
  2. 2023C-Pack: Packed Resources For General Chinese Embeddingscited by 556
  3. 2023LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compressioncited by 443
  4. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Modelscited by 423
  5. 2024LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compressioncited by 343
  6. 2023Large Language Models for Information Retrieval: A Surveycited by 331
  7. 2025WebThinker: Empowering Large Reasoning Models with Deep Research Capabilitycited by 320
  8. 2024We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?cited by 281
  9. 2023RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentationcited by 253
  10. 2022ASQA: Factoid Questions Meet Long-Form Answerscited by 231
  11. 2023How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Compositioncited by 222
  12. 2023Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificitycited by 204
  13. 2024RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generationcited by 144
  14. 2024xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Tokencited by 123
  15. 2019Deeper Text Understanding for IR with Contextual Neural Language Modelingcited by 111
  16. 2024LongAlign: A Recipe for Long Context Alignment of Large Language Modelscited by 102
  17. 2024From Matching to Generation: A Survey on Generative Information Retrievalcited by 89
  18. 2024Trustworthiness in Retrieval-Augmented Generation Systems: A Surveycited by 83
  19. 2024Prompt Compression for Large Language Models: A Surveycited by 65
  20. 2024CompAct: Compressing Retrieved Documents Actively for Question Answeringcited by 64
  21. 2023PRCA: Fitting Black-Box Large Language Models for Retrieval Question Answering via Pluggable Reward-Driven Contextual Adaptercited by 38
  22. 2024Small Models, Big Insights: Leveraging Slim Proxy Models To Decide When and What to Retrieve for LLMscited by 34
  23. 2024Grounding Language Model with Chunking-Free In-Context Retrievalcited by 30
  24. 2024BIDER: Bridging Knowledge Inconsistency for Efficient Retrieval-Augmented LLMs via Key Supporting Evidencecited by 28
  25. 2024RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generationcited by 20
  26. 2024INTERS: Unlocking the Power of Large Language Models in Search with Instruction Tuningcited by 19

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 13.

16 papers.

Sort:

By area:

  1. 2025DeepAgent: A General Reasoning Agent with Scalable Toolsetscited by 69
  2. 2025Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Taskscited by 62
  3. 2025Interact-RAG: Reason and Interact with the Corpus, Beyond Black-Box Retrievalcited by 6
  4. 2026Less is More for RAG: Information Gain Pruning for Generator-Aligned Reranking and Evidence Selectioncited by 3
  5. 2026BEAR: Budgeted Evidence Allocation for Multi-Document Reasoningcited by 1
  6. 2026Semantic Chunking and the Entropy of Natural Languagecited by 1
  7. 2026MM-BizRAG: Rethinking Multimodal Retrieval-Augmented Generation for General Purpose Enterprise Q&Acited by 1
  8. 2026Position: Multi-Agent Algorithmic Care Systems Demand Contestability for Trustworthy AIcited by 0
  9. 2026Developing Adaptive Context Compression Techniques for Large Language Models (LLMs) in Long-Running Interactionscited by 0
  10. 2026Hierarchical Abstract Tree for Cross-Document Retrieval-Augmented Generationcited by 0
  11. 2026Trace Only What You Need: Structure-Aware On-Demand Hypergraph Memory for Long-Document Question Answeringcited by 0
  12. 2026Storyline Trees: Hierarchical Representations for Long-Form Narrativescited by 0
4 more
  1. 2026Constraint-Aware Hierarchical Search for Regulation-Driven Fine-Grained Classificationcited by 0
  2. 2026Compression Beyond the Uncompressed: A Two-Stage Training Recipe for Soft Context Compression in RAGcited by 0
  3. 2026REVA: Reusable Evidence View Aggregation for Context-Efficient RAG Servingcited by 0
  4. 2026Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Stronger Baselines for Retrieval-Augmented Generation with Long-Context Language Models
  2. 2025MacRAG: Compress, Slice, and Scale-up for Multi-Scale Adaptive Context RAG
  3. 2026Fast and Faithful: Real-Time Verification for Long-Document Retrieval-Augmented Generation Systems
  4. 2025Grounding Long-Context Reasoning with Contextual Normalization for Retrieval-Augmented Generation
  5. 2025Does RAG Really Perform Bad For Long-Context Processing?
  6. 2024Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG
  7. 2024Long Context RAG Performance of Large Language Models
  8. 2025Fast or Better? Balancing Accuracy and Cost in Retrieval-Augmented Generation with Flexible User Control