Enhancing RAG Efficiency with Adaptive Context Compression

Abstract

Retrieval-augmented generation (RAG) enhances large language models (LLMs) with external knowledge but incurs significant inference costs due to lengthy retrieved contexts.While context compression mitigates this issue, existing methods apply fixed compression rates-over-compressing simple queries or under-compressing complex ones.We propose Adaptive Context Compression for RAG (ACC-RAG), a framework that dynamically adjusts compression rates based on input complexity, optimizing inference efficiency without loss of accuracy.ACC-RAG combines a hierarchical compressor (for multi-granular embeddings) with a context selector to retain minimal sufficient information, akin to human skimming.Evaluated on Wikipedia and five QA datasets, ACC-RAG outperforms fixed-rate methods and unlocks >4× faster inference versus standard RAG while maintaining or improving accuracy.

Authors 2

1. Shuyu Guo

   Shandong University

   Affiliation as printed

   Shandong University Qingdao , China

2. Zhaochun Ren Aachen

   Leiden University

   Affiliation as printed

   Leiden University Leiden , The Netherlands