Efficient Dynamic Clustering-Based Document Compression for Retrieval-Augmented-Generation
On the map: Retrieval-augmented generation → Generation and context integration
Abstract (arXiv)
Retrieval-Augmented Generation (RAG) has emerged as a widely adopted approach for knowledge injection during large language model (LLM) inference in recent years. However, due to their limited ability to exploit fine-grained inter-document relationships, current RAG implementations face challenges in effectively addressing the retrieved noise and redundancy content, which may cause error in the generation results. To address these limitations, we propose an Efficient Dynamic Clustering-based document Compression framework (EDC2-RAG) that utilizes latent inter-document relationships while simultaneously removing irrelevant information and redundant content. We validate our approach, built upon GPT-3.5-Turbo and GPT-4o-mini, on widely used knowledge-QA and Hallucination-Detection datasets. Experimental results show that our method achieves consistent performance improvements across various scenarios and experimental settings, demonstrating strong robustness and applicability. Our code and datasets are available at https://github.com/Tsinghua-dhy/EDC-2-RAG.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation. Builds on 38 of its 54 references that are in the map. First posted on arXiv 4 Apr 2025.
Builds on
38 of 54 references.
Closest ancestors · 5
Same direction, newest first
- 2023Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models15 Nov
- 2023TCRA-LLM: Token Compression Retrieval Augmented Large Language Model for Inference Cost Reduction24 Oct
- 2023RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation6 Oct
- 2022Atlas: Few-shot Learning with Retrieval Augmented Language Models5 Aug
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks22 May
Other references · 33
- 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
- 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
- 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
- 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
- 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
- 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
- 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
- 2021Improving language models by retrieving from trillions of tokenscited by 1,293
- 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
- 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 810
- 2020A Survey on Knowledge Graphs: Representation, Acquisition and Applicationscited by 643
- 2023Enabling Large Language Models to Generate Text with Citationscited by 595
21 more
- 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 532
- 2023LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compressioncited by 453
- 2022Unnatural Instructions: Tuning Language Models with (Almost) No Human Laborcited by 397
- 2021QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answeringcited by 388
- 2023Towards Expert-Level Medical Question Answering with Large Language Modelscited by 384
- 2023HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Modelscited by 341
- 2023LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Modelscited by 324
- 2024G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answeringcited by 223
- 2024Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agentscited by 218
- 2023Knowledge Graph Prompting for Multi-Document Question Answeringcited by 152
- 2023DISC-LawLLM: Fine-tuning Large Language Models for Intelligent Legal Servicescited by 120
- 2023Knowledge-Augmented Language Model Prompting for Zero-Shot Knowledge Graph Question Answeringcited by 119
- 2023Enhancing Uncertainty-Based Hallucination Detection with Stronger Focuscited by 99
- 2023FELM: Benchmarking Factuality Evaluation of Large Language Modelscited by 66
- 2023Knowledge Graph-Augmented Language Models for Knowledge-Grounded Dialogue Generationcited by 54
- 2023Do Large Language Models Know about Facts?cited by 51
- 2024REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answeringcited by 28
- 2024Citation-Enhanced Generation for LLM-based Chatbotscited by 25
- 2024A Collaborative Multi-Agent Approach to Retrieval-Augmented Generation Across Diverse Datacited by 10
- 2024Re3val: Reinforced and Reranked Generative Retrievalcited by 9
- 2024Coarse-to-Fine Highlighting: Reducing Knowledge Hallucination in Large Language Modelscited by 7
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2025Less Is More: Elevating RAG via Performance-Driven Context Compression
- 2025Cluster-based Adaptive Retrieval: Dynamic Context Selection for RAG Applications
- 2024Contextual Compression in Retrieval-Augmented Generation for Large Language Models: A Survey
- 2025Enhancing RAG Efficiency with Adaptive Context Compression
- 2026Rethinking Soft Compression in Retrieval-Augmented Generation: A Query-Conditioned Selector Perspective
- 2025Dynamic Parametric Retrieval Augmented Generation for Test-time Knowledge Enhancement
- 2025SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression
- 2025Knowledge Graph-Guided Retrieval Augmented Generation