# AttentionRAG: Attention-Guided Context Pruning in Retrieval-Augmented Generation

arXiv: https://arxiv.org/abs/2503.10720 · HTML: https://mlsanity.com/paper/2503.10720/

## Key facts

- Cited by 19 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 26 of its 36 references that are in the map.
- First posted on arXiv 13 Mar 2025.

## Placed in

- Retrieval-augmented generation / [Generation and context integration](https://mlsanity.com/rag/generation-and-context-integration/)

## Builds on (most cited first, 26 of 26)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [Learning to Compress Prompts with Gist Tokens](https://mlsanity.com/paper/2304.08467/) (2023)
- [LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression](https://mlsanity.com/paper/2403.12968/) (2024)
- [Efficient Attentions for Long Document Summarization](https://mlsanity.com/paper/2104.02112/) (2021)
- [RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation](https://mlsanity.com/paper/2310.04408/) (2023)
- [BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack](https://mlsanity.com/paper/2406.10149/) (2024)
- [xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token](https://mlsanity.com/paper/2405.13792/) (2024)
- [Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA](https://mlsanity.com/paper/2406.17419/) (2024)
- [Overcoming a Theoretical Limitation of Self-Attention](https://mlsanity.com/paper/2202.12172/) (2022)
- [Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization](https://mlsanity.com/paper/2406.16008/) (2024)
- [ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents](https://mlsanity.com/paper/2502.18017/) (2025)
- [RAG-QA Arena: Evaluating Domain Robustness for Long-form Retrieval Augmented Question Answering](https://mlsanity.com/paper/2407.13998/) (2024)
- [Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selection](https://mlsanity.com/paper/2405.16178/) (2024)
- [Attend First, Consolidate Later: On the Importance of Attention in Different LLM Layers](https://mlsanity.com/paper/2409.03621/) (2024)
- [RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructions](https://mlsanity.com/paper/2501.00353/) (2024)
- [Enhancing Retrieval and Managing Retrieval: A Four-Module Synergy for Improved Quality and Efficiency in RAG Systems](https://mlsanity.com/paper/2407.10670/) (2024)
- [Contextual Compression in Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2409.13385/) (2024)

## Built on by (most cited first, 19 of 19)

- [VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning](https://mlsanity.com/paper/2505.22019/) (2025)
- [SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents](https://mlsanity.com/paper/2601.16746/) (2026)
- [LongCodeZip: Compress Long Context for Code Language Models](https://mlsanity.com/paper/2510.00446/) (2025)
- [Enhancing Financial Report Question-Answering: A Retrieval-Augmented Generation System with Reranking Analysis](https://mlsanity.com/paper/2603.16877/) (2026)
- [RaCoT: Plug-and-Play Contrastive Example Generation Mechanism for Enhanced LLM Reasoning Reliability](https://mlsanity.com/paper/2510.22710/) (2025)
- [Reasoning in Trees: Improving Retrieval-Augmented Generation for Multi-Hop Question Answering](https://mlsanity.com/paper/2601.11255/) (2026)
- [COMI: Coarse-to-fine Context Compression via Marginal Information Gain](https://mlsanity.com/paper/2602.01719/) (2026)
- [Sustainable Hybrid Document-Routed Retrieval for Financial RAG: Resolving the Robustness-Precision Trade-off](https://mlsanity.com/paper/2603.26815/) (2026)
- [FASA: Frequency-aware Sparse Attention](https://mlsanity.com/paper/2602.03152/) (2026)
- [VimRAG: Navigating Massive Visual Context in Retrieval-Augmented Generation via Multimodal Memory Graph](https://mlsanity.com/paper/2602.12735/) (2026)
- [SWE-Pruner Pro: The Coder LLM Already Knows What to Prune](https://mlsanity.com/paper/2607.18213/) (2026)
- [D2Plan: Dual-Agent Dynamic Global Planning for Complex Retrieval-Augmented Reasoning](https://mlsanity.com/paper/2601.08282/) (2026)
- [Mapping Text to Multiplex Graph: Prompt Compression as L'evy Walk-Guided Graph Pruning](https://mlsanity.com/paper/2607.01241/) (2026)
- [The Virtuous Cycle: AI-Powered Vector Search and Vector Search-Augmented AI](https://mlsanity.com/paper/2603.09347/) (2026)
- [Efficient Retrieval-Augmented Generation via Token Co-occurrence Graphs](https://mlsanity.com/paper/2606.30093/) (2026)
- [Compression Beyond the Uncompressed: A Two-Stage Training Recipe for Soft Context Compression in RAG](https://mlsanity.com/paper/2609.05152/) (2026)
- [ARSM: Auto-Regressive State Machine for Agentic Reasoning Compression](https://mlsanity.com/paper/2609.32852/) (2026)
- [EntroPrefill: Renyi-Guided Context Pruning with Conditional Stability Guarantees for Retrieval-Augmented Generation](https://mlsanity.com/paper/2610.09757/) (2026)
- [Clarify, Then Focus: Statement Normalization for Conversation Analytics at Scale](https://mlsanity.com/paper/2610.10758/) (2026)

## Abstract (arXiv)

While RAG demonstrates remarkable capabilities in LLM applications, its effectiveness is hindered by the ever-increasing length of retrieved contexts, which introduces information redundancy and substantial computational overhead. Existing context pruning methods, such as LLMLingua, lack contextual awareness and offer limited flexibility in controlling compression rates, often resulting in either insufficient pruning or excessive information loss. In this paper, we propose AttentionRAG, an attention-guided context pruning method for RAG systems. The core idea of AttentionRAG lies in its attention focus mechanism, which reformulates RAG queries into a next-token prediction paradigm. This mechanism isolates the query's semantic focus to a single token, enabling precise and efficient attention calculation between queries and retrieved contexts. Extensive experiments on LongBench and Babilong benchmarks show that AttentionRAG achieves up to 6.3× context compression while outperforming LLMLingua methods by around 10% in key metrics.