# EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generation

arXiv: https://arxiv.org/abs/2412.12559 · HTML: https://mlsanity.com/paper/2412.12559/

## Key facts

- Cited by 17 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 49 of its 73 references that are in the map.
- First posted on arXiv 17 Dec 2024.

## Placed in

- Retrieval-augmented generation / [Generation and context integration](https://mlsanity.com/rag/generation-and-context-integration/)
- Efficient LLM inference and serving / [Prompt and context compression](https://mlsanity.com/inference/prompt-and-context-compression/)

## Builds on (most cited first, 30 of 49)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [Generalization through Memorization: Nearest Neighbor Language Models](https://mlsanity.com/paper/1911.00172/) (2019)
- [REPLUG: Retrieval-Augmented Black-Box Language Models](https://mlsanity.com/paper/2301.12652/) (2023)
- [In-Context Retrieval-Augmented Language Models](https://mlsanity.com/paper/2302.00083/) (2023)
- [Passage Re-ranking with BERT](https://mlsanity.com/paper/1901.04085/) (2019)
- [LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression](https://mlsanity.com/paper/2310.06839/) (2023)
- [Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity](https://mlsanity.com/paper/2403.14403/) (2024)
- [Learning to Compress Prompts with Gist Tokens](https://mlsanity.com/paper/2304.08467/) (2023)
- [Adapting Language Models to Compress Contexts](https://mlsanity.com/paper/2305.14788/) (2023)
- [LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression](https://mlsanity.com/paper/2403.12968/) (2024)
- [Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy](https://mlsanity.com/paper/2305.15294/) (2023)
- [Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP](https://mlsanity.com/paper/2212.14024/) (2022)
- [Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting](https://mlsanity.com/paper/2306.17563/) (2023)
- [Fine-Tuning LLaMA for Multi-Stage Text Retrieval](https://mlsanity.com/paper/2310.08319/) (2023)
- [Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding](https://mlsanity.com/paper/2401.07851/) (2024)
- [Towards a Unified Multi-Dimensional Evaluator for Text Generation](https://mlsanity.com/paper/2210.07197/) (2022)

## Built on by (most cited first, 17 of 17)

- [COMI: Coarse-to-fine Context Compression via Marginal Information Gain](https://mlsanity.com/paper/2602.01719/) (2026)
- [SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression](https://mlsanity.com/paper/2507.05633/) (2025)
- [S2G-RAG: Structured Sufficiency and Gap Judging for Iterative Retrieval-Augmented QA](https://mlsanity.com/paper/2604.23783/) (2026)
- [Beyond Hard and Soft: Hybrid Context Compression for Balancing Local and Global Information Retention](https://mlsanity.com/paper/2505.15774/) (2025)
- [CompLLM: Compression for Long Context Q&A](https://mlsanity.com/paper/2509.19228/) (2025)
- [HetaRAG: Hybrid Deep Retrieval-Augmented Generation across Heterogeneous Data Stores](https://mlsanity.com/paper/2509.21336/) (2025)
- [Beyond Position Bias: Shifting Context Compression from Position-Driven to Semantic-Driven](https://mlsanity.com/paper/2605.09463/) (2026)
- [Aligning Extraction and Generation for Robust Retrieval-Augmented Generation](https://mlsanity.com/paper/2503.04789/) (2025)
- [When More Retrieval Hurts: Retrieval-Augmented Code Review Generation](https://mlsanity.com/paper/2511.05302/) (2025)
- [Data Distribution Matters: A Data-Centric Perspective on Context Compression for Large Language Model](https://mlsanity.com/paper/2602.01778/) (2026)
- [Prism-Reranker: Beyond Relevance Scoring -- Jointly Producing Contributions and Evidence for Agentic Retrieval](https://mlsanity.com/paper/2604.23734/) (2026)
- [Fixed RAG Compression Collapses Measured Reader Scaling](https://mlsanity.com/paper/2606.21807/) (2026)
- [Lost in Compression: A Controlled Cross-Lingual Audit of Extractive Prompt Compressors](https://mlsanity.com/paper/2608.26175/) (2026)
- [ConCise: Training-Free Conclusion-Chain State Compression for Cost-Efficient Multi-Step RAG Services](https://mlsanity.com/paper/2606.28361/) (2026)
- [Compression Beyond the Uncompressed: A Two-Stage Training Recipe for Soft Context Compression in RAG](https://mlsanity.com/paper/2609.05152/) (2026)
- [REVA: Reusable Evidence View Aggregation for Context-Efficient RAG Serving](https://mlsanity.com/paper/2609.11209/) (2026)
- [MORSE: Multi-Context Ordering via Reverse Scoring for Evidence-Preserving Compression](https://mlsanity.com/paper/2609.27380/) (2026)

## Abstract (arXiv)

We introduce EXIT, an extractive context compression framework that enhances both the effectiveness and efficiency of retrieval-augmented generation (RAG) in question answering (QA). Current RAG systems often struggle when retrieval models fail to rank the most relevant documents, leading to the inclusion of more context at the expense of latency and accuracy. While abstractive compression methods can drastically reduce token counts, their token-by-token generation process significantly increases end-to-end latency. Conversely, existing extractive methods reduce latency but rely on independent, non-adaptive sentence selection, failing to fully utilize contextual information. EXIT addresses these limitations by classifying sentences from retrieved documents - while preserving their contextual dependencies - enabling parallelizable, context-aware extraction that adapts to query complexity and retrieval quality. Our evaluations on both single-hop and multi-hop QA tasks show that EXIT consistently surpasses existing compression methods and even uncompressed baselines in QA accuracy, while also delivering substantial reductions in inference time and token count. By improving both effectiveness and efficiency, EXIT provides a promising direction for developing scalable, high-quality QA solutions in RAG pipelines. Our code is available at https://github.com/ThisIsHwang/EXIT