# PoC: Performance-oriented Context Compression for Large Language Models via Performance Prediction

arXiv: https://arxiv.org/abs/2603.19733 · HTML: https://mlsanity.com/paper/2603.19733/

## Key facts

- Cited by 3 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 21 of its 35 references that are in the map.
- First posted on arXiv 20 Mar 2026.

## Placed in

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

## Builds on (most cited first, 21 of 21)

- [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)
- [LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression](https://mlsanity.com/paper/2310.06839/) (2023)
- [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)
- [Efficient Attentions for Long Document Summarization](https://mlsanity.com/paper/2104.02112/) (2021)
- [SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine](https://mlsanity.com/paper/1704.05179/) (2017)
- [Long Context Compression with Activation Beacon](https://mlsanity.com/paper/2401.03462/) (2024)
- [Prompt Compression and Contrastive Conditioning for Controllability and Toxicity Reduction in Language Models](https://mlsanity.com/paper/2210.03162/) (2022)
- [Retaining Key Information under High Compression Ratios: Query-Guided Compressor for LLMs](https://mlsanity.com/paper/2406.02376/) (2024)
- [Perception Compressor: A Training-Free Prompt Compression Framework in Long Context Scenarios](https://mlsanity.com/paper/2409.19272/) (2024)
- [DAST: Context-Aware Compression in LLMs via Dynamic Allocation of Soft Tokens](https://mlsanity.com/paper/2502.11493/) (2025)
- [Question Answering Survey: Directions, Challenges, Datasets, Evaluation Matrices](https://mlsanity.com/paper/2112.03572/) (2021)
- [Autoencoding-Free Context Compression for LLMs via Contextual Semantic Anchors](https://mlsanity.com/paper/2510.08907/) (2025)
- [Forgetting Curve: A Reliable Method for Evaluating Memorization Capability for Long-context Models](https://mlsanity.com/paper/2410.04727/) (2024)
- [COMI: Coarse-to-fine Context Compression via Marginal Information Gain](https://mlsanity.com/paper/2602.01719/) (2026)
- [Enhancing RAG Efficiency with Adaptive Context Compression](https://mlsanity.com/paper/2507.22931/) (2025)
- [CoMeT: Collaborative Memory Transformer for Efficient Long Context Modeling](https://mlsanity.com/paper/2602.01766/) (2026)

## Built on by (most cited first, 3 of 3)

- [MemoSight: Unifying Context Compression and Multi Token Prediction for Reasoning Acceleration](https://mlsanity.com/paper/2604.14889/) (2026)
- [HybridThinker: Efficient Chain-of-Thought Reasoning via Compressed Memory and Transient Thought Steps](https://mlsanity.com/paper/2606.03768/) (2026)
- [Compression Beyond the Uncompressed: A Two-Stage Training Recipe for Soft Context Compression in RAG](https://mlsanity.com/paper/2609.05152/) (2026)

## Abstract (arXiv)

While context compression can mitigate the growing inference costs of Large Language Models (LLMs) by shortening contexts, existing methods that specify a target compression ratio or length suffer from unpredictable performance degradation, hindering their reliable deployment. We introduce a paradigm shift to Performance-oriented Context Compression (PoC), where developers specify an acceptable performance floor instead of a compression ratio. PoC employs a lightweight performance predictor to automatically find the most aggressive compression ratio that satisfies this constraint before steering an off-the-shelf compressor. We design and compare two predictor variants: a simple context-agnostic predictor and a more sophisticated context-aware one that considers the input's inherent compressibility. On both question-answering and summarization benchmarks, the context-aware predictor consistently achieves lower performance prediction error than the context-agnostic predictor, while the resulting context-aware PoC attains a superior overall performance. Our work paves the way for a more reliable, efficient, and performance-aware deployment of context compression for LLMs.