mlsanityData to 7 Oct 2026

Contextual Compression in Retrieval-Augmented Generation for Large Language Models: A Survey

arXiv 2409.13385 ↗First posted 20 Sep 2024cs.CL cs.IRcited by 5

On the map: Retrieval-augmented generation → Generation and context integration

Abstract (arXiv)

Large Language Models (LLMs) showcase remarkable abilities, yet they struggle with limitations such as hallucinations, outdated knowledge, opacity, and inexplicable reasoning. To address these challenges, Retrieval-Augmented Generation (RAG) has proven to be a viable solution, leveraging external databases to improve the consistency and coherence of generated content, especially valuable for complex, knowledge-rich tasks, and facilitates continuous improvement by leveraging domain-specific insights. By combining the intrinsic knowledge of LLMs with the vast, dynamic repositories of external databases, RAG achieves a synergistic effect. However, RAG is not without its limitations, including a limited context window, irrelevant information, and the high processing overhead for extensive contextual data. In this comprehensive work, we explore the evolution of Contextual Compression paradigms, providing an in-depth examination of the field. Finally, we outline the current challenges and suggest potential research and development directions, paving the way for future advancements in this area.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation. Builds on 38 of its 60 references that are in the map. First posted on arXiv 20 Sep 2024.

Builds on

38 of 60 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Models5 Aug

Other references · 37

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  4. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  5. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  6. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  7. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
  8. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  9. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  10. 2020Longformer: The Long-Document Transformercited by 3,362
  11. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,424
  12. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
25 more
  1. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,830
  2. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,462
  3. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  4. 2021A General Language Assistant as a Laboratory for Alignmentcited by 1,023
  5. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 871
  6. 2022Simplified State Space Layers for Sequence Modelingcited by 776
  7. 2023Extending Context Window of Large Language Models via Positional Interpolationcited by 721
  8. 2020Pre-trained Models for Natural Language Processing: A Surveycited by 504
  9. 2022Hungry Hungry Hippos: Towards Language Modeling with State Space Modelscited by 495
  10. 2023LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compressioncited by 443
  11. 2023Hyena Hierarchy: Towards Larger Convolutional Language Modelscited by 388
  12. 2023Learning to Compress Prompts with Gist Tokenscited by 379
  13. 2023Adapting Language Models to Compress Contextscited by 350
  14. 2024LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compressioncited by 343
  15. 2021Factual Probing Is [MASK]: Learning vs. Learning to Recallcited by 291
  16. 2021Symbolic Knowledge Distillation: from General Language Models to Commonsense Modelscited by 270
  17. 2023Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuningcited by 171
  18. 2021Meta-learning via Language Model In-context Tuningcited by 163
  19. 2018Dissecting Contextual Word Embeddings: Architecture and Representationcited by 146
  20. 2022Prompt Compression and Contrastive Conditioning for Controllability and Toxicity Reduction in Language Modelscited by 96
  21. 2023RecurrentGPT: Interactive Generation of (Arbitrarily) Long Textcited by 84
  22. 2023Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Surveycited by 71
  23. 2023RECALL: A Benchmark for LLMs Robustness against External Counterfactual Knowledgecited by 51
  24. 2023Extending Context Window of Large Language Models via Semantic Compressioncited by 45
  25. 2024Compressing Long Context for Enhancing RAG with AMR-based Concept Distillationcited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 1.

5 papers.

  1. 2025AttentionRAG: Attention-Guided Context Pruning in Retrieval-Augmented Generationcited by 19
  2. 2026Rethinking Soft Compression in Retrieval-Augmented Generation: A Query-Conditioned Selector Perspectivecited by 4
  3. 2025Cost-Aware Retrieval-Augmentation Reasoning Models with Adaptive Retrieval Depthcited by 2
  4. 2024A Survey of Query Optimization in Large Language Modelscited by 1
  5. 2025CCF: A Context Compression Framework for Efficient Long-Sequence Language Modelingcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025When Retrieval Succeeds and Fails: Rethinking Retrieval-Augmented Generation for LLMs
  2. 2025Enhancing RAG Efficiency with Adaptive Context Compression
  3. 2025Less Is More: Elevating RAG via Performance-Driven Context Compression
  4. 2025SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression
  5. 2024A Survey on Retrieval-Augmented Text Generation for Large Language Models
  6. 2024Long Context RAG Performance of Large Language Models
  7. 2025Enhancing Retrieval-Augmented Generation: A Study of Best Practices
  8. 2024Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG