# Perception Compressor: A Training-Free Prompt Compression Framework in Long Context Scenarios

arXiv: https://arxiv.org/abs/2409.19272 · HTML: https://mlsanity.com/paper/2409.19272/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Placed in Prompt and context compression, one of 12 directions in Efficient LLM inference and serving.
- Builds on 19 of its 39 references that are in the map.
- First posted on arXiv 28 Sep 2024.

## Placed in

- Efficient LLM inference and serving / [Prompt and context compression](https://mlsanity.com/inference/prompt-and-context-compression/)

## Builds on (most cited first, 19 of 19)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression](https://mlsanity.com/paper/2310.06839/) (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)
- [RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation](https://mlsanity.com/paper/2310.04408/) (2023)
- [Focused Transformer: Contrastive Training for Context Scaling](https://mlsanity.com/paper/2307.03170/) (2023)
- [Unlimiformer: Long-Range Transformers with Unlimited Length Input](https://mlsanity.com/paper/2305.01625/) (2023)
- [xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token](https://mlsanity.com/paper/2405.13792/) (2024)
- [Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents](https://mlsanity.com/paper/2310.19923/) (2023)
- [Learning to Compress Prompt in Natural Language Formats](https://mlsanity.com/paper/2402.18700/) (2024)
- [Can Perplexity Reflect Large Language Model's Ability in Long Text Understanding?](https://mlsanity.com/paper/2405.06105/) (2024)
- [Context Embeddings for Efficient Answer Generation in RAG](https://mlsanity.com/paper/2407.09252/) (2024)
- [Retaining Key Information under High Compression Ratios: Query-Guided Compressor for LLMs](https://mlsanity.com/paper/2406.02376/) (2024)

## Built on by (most cited first, 23 of 23)

- [Natural-Language Agent Harnesses](https://mlsanity.com/paper/2603.25723/) (2026)
- [DAST: Context-Aware Compression in LLMs via Dynamic Allocation of Soft Tokens](https://mlsanity.com/paper/2502.11493/) (2025)
- [GMSA: Enhancing Context Compression via Group Merging and Layer Semantic Alignment](https://mlsanity.com/paper/2505.12215/) (2025)
- [Autoencoding-Free Context Compression for LLMs via Contextual Semantic Anchors](https://mlsanity.com/paper/2510.08907/) (2025)
- [COMI: Coarse-to-fine Context Compression via Marginal Information Gain](https://mlsanity.com/paper/2602.01719/) (2026)
- [Read As Human: Compressing Context via Parallelizable Close Reading and Skimming](https://mlsanity.com/paper/2602.01840/) (2026)
- [CompLLM: Compression for Long Context Q&A](https://mlsanity.com/paper/2509.19228/) (2025)
- [CoMeT: Collaborative Memory Transformer for Efficient Long Context Modeling](https://mlsanity.com/paper/2602.01766/) (2026)
- [SemantiCache: Efficient KV Cache Compression via Semantic Chunking and Clustered Merging](https://mlsanity.com/paper/2603.14303/) (2026)
- [From Token to Line: Enhancing Code Generation with a Long-Term Perspective](https://mlsanity.com/paper/2504.07433/) (2025)
- [PoC: Performance-oriented Context Compression for Large Language Models via Performance Prediction](https://mlsanity.com/paper/2603.19733/) (2026)
- [Beyond Position Bias: Shifting Context Compression from Position-Driven to Semantic-Driven](https://mlsanity.com/paper/2605.09463/) (2026)
- [RAISE: Reinforced Adaptive Instruction Selection For Large Language Models](https://mlsanity.com/paper/2504.07282/) (2025)
- [Length-Adaptive Interest Network for Balancing Long and Short Sequence Modeling in CTR Prediction](https://mlsanity.com/paper/2601.19142/) (2026)
- [Data Distribution Matters: A Data-Centric Perspective on Context Compression for Large Language Model](https://mlsanity.com/paper/2602.01778/) (2026)
- [SAGE: A Quantitative Evaluation of Socialized Evolution in Agent Ecosystems](https://mlsanity.com/paper/2606.03544/) (2026)
- [Mapping Text to Multiplex Graph: Prompt Compression as L'evy Walk-Guided Graph Pruning](https://mlsanity.com/paper/2607.01241/) (2026)
- [PEMUTA: Pedagogically-Enriched Multi-Granular Undergraduate Thesis Assessment](https://mlsanity.com/paper/2507.19556/) (2025)
- [When Hard Negatives Hurt: Bridging the Generative-Discriminative Gap in Hard Negative Synthesis for Retrieval](https://mlsanity.com/paper/2606.01304/) (2026)
- [HybridThinker: Efficient Chain-of-Thought Reasoning via Compressed Memory and Transient Thought Steps](https://mlsanity.com/paper/2606.03768/) (2026)
- [Relevant but Incomplete: Referential Dangling as a Paradigm-Level Failure Mode in Hard Prompt Compression](https://mlsanity.com/paper/2608.04569/) (2026)
- [Compression Beyond the Uncompressed: A Two-Stage Training Recipe for Soft Context Compression in RAG](https://mlsanity.com/paper/2609.05152/) (2026)
- [SuPER-Mamba: Surprisal Prioritization for Extended-Context Routing in Mamba](https://mlsanity.com/paper/2610.16636/) (2026)

## Abstract (arXiv)

Large language models (LLMs) demonstrate exceptional capabilities in various scenarios. However, they suffer from much redundant information and are sensitive to the position of key information in long context scenarios. To address these challenges, we present Perception Compressor, a training-free prompt compression framework. It includes a perception retriever that leverages guiding questions and instruction to retrieve the most relevant demonstrations, a dual-slope ratio allocator to dynamically allocate compression ratios and open-book ratios, and a semi-guided iterative compression that retains key information at the token level while removing tokens that distract the LLM. We conduct extensive experiments on long context benchmarks, i.e., NaturalQuestions, LongBench, and MuSiQue. Experiment results show that Perception Compressor outperforms existing methods by a large margin, achieving state-of-the-art performance.