mlsanityData to 7 Oct 2026

CompAct: Compressing Retrieved Documents Actively for Question Answering

arXiv 2407.09014 ↗First posted 12 Jul 2024cs.CLcited by 64

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

Abstract (arXiv)

Retrieval-augmented generation supports language models to strengthen their factual groundings by providing external contexts. However, language models often face challenges when given extensive information, diminishing their effectiveness in solving questions. Context compression tackles this issue by filtering out irrelevant information, but current methods still struggle in realistic scenarios where crucial information cannot be captured with a single-step approach. To overcome this limitation, we introduce CompAct, a novel framework that employs an active strategy to condense extensive documents without losing key information. Our experiments demonstrate that CompAct brings significant improvements in both performance and compression rate on multi-hop question-answering benchmarks. CompAct flexibly operates as a cost-efficient plug-in module with various off-the-shelf retrievers or readers, achieving exceptionally high compression rates (47x).

Key facts. Cited by 64 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 30 of its 49 references that are in the map. First posted on arXiv 12 Jul 2024.

Builds on

30 of 49 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token22 May
  2. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Models5 Aug
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks22 May

Other references · 27

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  5. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  6. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  7. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  8. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,201
  9. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,883
  10. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
  11. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  12. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
15 more
  1. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 788
  2. 2024Yi: Open Foundation Models by 01.AIcited by 706
  3. 2023LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compressioncited by 443
  4. 2023Learning to Compress Prompts with Gist Tokenscited by 379
  5. 2023Adapting Language Models to Compress Contextscited by 350
  6. 2024LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compressioncited by 343
  7. 2024Long-context LLMs Struggle with Long In-context Learningcited by 285
  8. 2020HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Datacited by 263
  9. 2024Chain of Agents: Large Language Models Collaborating on Long-Context Taskscited by 201
  10. 2023Knowledge Graph Prompting for Multi-Document Question Answeringcited by 150
  11. 2024A Human-Inspired Reading Agent with Gist Memory of Very Long Contextscited by 140
  12. 2023Walking Down the Memory Maze: Beyond Context Limit through Interactive Readingcited by 129
  13. 2024Make Your LLM Fully Utilize the Contextcited by 118
  14. 2024Retaining Key Information under High Compression Ratios: Query-Guided Compressor for LLMscited by 24
  15. 2024Are Long-LLMs A Necessity For Long-Context Tasks?cited by 22

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 28; 2026: 31.

64 papers.

Sort:

By area:

  1. 2025MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agentscited by 226
  2. 2024Prompt Compression for Large Language Models: A Surveycited by 65
  3. 2024Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Modelscited by 57
  4. 2025A Survey of Multimodal Retrieval-Augmented Generationcited by 37
  5. 2025Provence: efficient and robust context pruning for retrieval-augmented generationcited by 25
  6. 2026AgentOCR: Reimagining Agent History via Optical Self-Compressioncited by 22
  7. 2025GMSA: Enhancing Context Compression via Group Merging and Layer Semantic Alignmentcited by 20
  8. 2024EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generationcited by 17
  9. 2025Hierarchical Document Refinement for Long-context Retrieval-augmented Generationcited by 16
  10. 2025MEMTRACK: Evaluating Long-Term Memory and State Tracking in Multi-Platform Dynamic Agent Environmentscited by 13
  11. 2026COMI: Coarse-to-fine Context Compression via Marginal Information Gaincited by 13
  12. 2025R3Mem: Bridging Memory Retention and Retrieval via Reversible Compressioncited by 12
38 more
  1. 2025VTCBench: Can Vision-Language Models Understand Long Context with Vision-Text Compression?cited by 11
  2. 2026Read As Human: Compressing Context via Parallelizable Close Reading and Skimmingcited by 10
  3. 2025SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compressioncited by 9
  4. 2025AdmTree: Compressing Lengthy Context with Adaptive Semantic Treescited by 7
  5. 2025GORAG: Graph-based Online Retrieval Augmented Generation for Dynamic Few-shot Social Media Text Classificationcited by 6
  6. 2025HawkBench: Investigating Resilience of RAG Methods on Stratified Information-Seeking Taskscited by 6
  7. 2025SCOPE: A Generative Approach for LLM Prompt Compressioncited by 6
  8. 2026CoMeT: Collaborative Memory Transformer for Efficient Long Context Modelingcited by 5
  9. 2026Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compressioncited by 5
  10. 2024Familiarity-Aware Evidence Compression for Retrieval-Augmented Generationcited by 4
  11. 2025OSCAR: Online Soft Compression And Rerankingcited by 4
  12. 2025ECoRAG: Evidentiality-guided Compression for Long Context RAGcited by 4
  13. 2026End-to-End Context Compression at Scalecited by 4
  14. 2025Efficient Knowledge Probing of Large Language Models by Adapting Pre-trained Embeddingscited by 3
  15. 2026MARA: A Multimodal Adaptive Retrieval-Augmented Framework for Document Question Answeringcited by 3
  16. 2026Beyond Position Bias: Shifting Context Compression from Position-Driven to Semantic-Drivencited by 3
  17. 2026Organize then Retrieve: Hierarchical Memory Navigation for Efficient Agentscited by 3
  18. 2025OkraLong: A Flexible Retrieval-Augmented Framework for Long-Text Query Processingcited by 2
  19. 2025Aligning Extraction and Generation for Robust Retrieval-Augmented Generationcited by 2
  20. 2025Context-Efficient Retrieval with Factual Decompositioncited by 2
  21. 2025AttnComp: Attention-Guided Adaptive Context Compression for Retrieval-Augmented Generationcited by 2
  22. 2025MuISQA: Multi-Intent Retrieval-Augmented Generation for Scientific Question Answeringcited by 2
  23. 2026XProvence: Zero-Cost Multilingual Context Pruning for Retrieval-Augmented Generationcited by 2
  24. 2024Boosting Long-Context Management via Query-Guided Activation Refillingcited by 1
  25. 2025Oreo: A Plug-in Context Reconstructor to Enhance Retrieval-Augmented Generationcited by 1
  26. 2025ACoRN: Noise-Robust Abstractive Compression in Retrieval-Augmented Language Modelscited by 1
  27. 2025LoopServe: An Adaptive Dual-phase LLM Inference Acceleration System for Multi-Turn Dialoguescited by 1
  28. 2025Smooth Reading: Bridging the Gap of Recurrent LLM to Self-Attention LLM on Long-Context Taskscited by 1
  29. 2025Relevance to Utility: Process-Supervised Rewrite for RAGcited by 1
  30. 2026Data Distribution Matters: A Data-Centric Perspective on Context Compression for Large Language Modelcited by 1
  31. 2026EnComp: Lightweight Encoder-Only Context Compression for Retrieval-Augmented Question Answeringcited by 1
  32. 2026DiffuMask: Diffusion Language Model for Token-level Prompt Pruningcited by 1
  33. 2026Prism-Reranker: Beyond Relevance Scoring -- Jointly Producing Contributions and Evidence for Agentic Retrievalcited by 1
  34. 2026Fixed RAG Compression Collapses Measured Reader Scalingcited by 1
  35. 2026ContextSniper: AntTrail's Token-Efficient Code Memory for Repository-Level Program Repaircited by 1
  36. 2026IterCOMP: Reasoning-aware Adaptive Prompt Compression for Multi-hop Question Answeringcited by 1
  37. 2025Cmprsr: Abstractive Token-Level Question-Agnostic Prompt Compressorcited by 0
  38. 2025Noise-Robust Abstractive Compression in Retrieval-Augmented Language Modelscited by 0

50 most cited of 64 All 64 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025BRIEF-Pro: Universal Context Compression with Short-to-Long Synthesis for Fast and Accurate Multi-Hop Reasoning
  2. 2025PISCO: Pretty Simple Compression for Retrieval-Augmented Generation
  3. 2026Less is More: Lightweight Prompt Compression for Question Answering Applications on Edge Devices
  4. 2024BRIEF: Bridging Retrieval and Inference for Multi-hop Reasoning via Compression
  5. 2024Contextual Compression in Retrieval-Augmented Generation for Large Language Models: A Survey
  6. 2025CLaRa: Bridging Retrieval and Generation with Continuous Latent Reasoning
  7. 2024Lighter And Better: Towards Flexible Context Adaptation For Retrieval Augmented Generation
  8. 2023RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation