mlsanityData to 14 Oct 2026

AttnComp: Attention-Guided Adaptive Context Compression for Retrieval-Augmented Generation

arXiv 2509.17486 ↗First posted 22 Sep 2025cs.CLcited by 3

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

also in 1 more
Abstract (arXiv)

Retrieval-augmented generation improves the factual accuracy of Large Language Models (LLMs) by incorporating external context, but often suffers from irrelevant retrieved content that hinders effectiveness. Context compression addresses this issue by filtering out irrelevant information from context before LLM generation. However, existing methods struggle to adaptively adjust compression rates for different context, maintain low latency and integrate information across multiple documents. To overcome these limitations, We introduce AttnComp, an adaptive, efficient and context-aware compression framework. By leveraging the attention mechanism of LLMs to identify relevant information, AttnComp employs a Top-P compression algorithm to retain the minimal set of documents whose cumulative attention weights exceeds a predefined threshold. In addition to compression, AttnComp estimates response confidence by assessing the overall relevance of the retrieved content, enabling users to gauge response reliability. Experiments demonstrate that AttnComp outperforms existing compression methods and uncompressed baselines, achieving higher accuracy with substantial compression rates and lower latency.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation. Builds on 29 of its 41 references that are in the map. First posted on arXiv 22 Sep 2025.

Builds on

29 of 41 references.

Closest ancestors · 7

Same direction, newest first

  1. 2024CompAct: Compressing Retrieved Documents Actively for Question Answering12 Jul
  2. 2023RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation6 Oct
  3. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Context2 Oct
  4. 2023In-Context Retrieval-Augmented Language Models31 Jan
  5. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories20 Dec
  6. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Models5 Aug
  7. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks22 May

Other references · 22

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  4. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  5. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  6. 2023Efficient Streaming Language Models with Attention Sinkscited by 2,186
  7. 2024Qwen2 Technical Reportcited by 2,120
  8. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  9. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  10. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  11. 2021DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharingcited by 1,254
  12. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,253
10 more
  1. 2024SnapKV: LLM Knows What You are Looking for Before Generationcited by 880
  2. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 841
  3. 2023LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compressioncited by 453
  4. 2023A Survey of Confidence Estimation and Calibration in Large Language Modelscited by 256
  5. 2024Retrieval Head Mechanistically Explains Long-Context Factualitycited by 232
  6. 2023LooGLE: Can Long-Context Language Models Understand Long Contexts?cited by 202
  7. 2024FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Researchcited by 166
  8. 2024Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAGcited by 123
  9. 2024Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoningcited by 97
  10. 2024Controlling Risk of Retrieval-augmented Generation: A Counterfactual Prompting Frameworkcited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Beyond Position Bias: Shifting Context Compression from Position-Driven to Semantic-Drivencited by 3
  2. 2026ZipRL: Adaptive Multi-Turn Context Compression with Hindsight Response Replaycited by 3
  3. 2026REVA: Reusable Evidence View Aggregation for Context-Efficient RAG Servingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression
  2. 2024Contextual Compression in Retrieval-Augmented Generation for Large Language Models: A Survey
  3. 2024Enhancing and Accelerating Large Language Models via Instruction-Aware Contextual Compression
  4. 2025Enhancing RAG Efficiency with Adaptive Context Compression
  5. 2025No Mean Feat: Simple, Strong Baselines for Context Compression
  6. 2025ACoRN: Noise-Robust Abstractive Compression in Retrieval-Augmented Language Models
  7. 2026Developing Adaptive Context Compression Techniques for Large Language Models (LLMs) in Long-Running Interactions
  8. 2025Noise-Robust Abstractive Compression in Retrieval-Augmented Language Models