OSCAR: Online Soft Compression And Reranking
This addresses efficiency bottlenecks in RAG systems for users of large language models, representing a novel method for a known bottleneck rather than a foundational advancement.
The paper tackles the computational expense of scaling Retrieval-Augmented Generation (RAG) pipelines by introducing OSCAR, a query-dependent online soft compression method that reduces overhead while preserving performance, achieving a 2-5x speed-up in inference with minimal accuracy loss for LLMs up to 24B parameters.
Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by integrating external knowledge, leading to improved accuracy and relevance. However, scaling RAG pipelines remains computationally expensive as retrieval sizes grow. To address this, we introduce OSCAR, a novel query-dependent online soft compression method that reduces computational overhead while preserving performance. Unlike traditional hard compression methods, which shorten retrieved texts, or soft compression approaches, which map documents to continuous embeddings offline, OSCAR dynamically compresses retrieved information at inference time, eliminating storage overhead and enabling higher compression rates. Additionally, we extend OSCAR to simultaneously perform reranking, further optimizing the efficiency of the RAG pipeline. Our experiments demonstrate state-of-the-art performance with a 2-5x speed-up in inference and minimal to no loss in accuracy for LLMs ranging from 1B to 24B parameters. The models are available at: https://huggingface.co/collections/naver/oscar-67d446a8e3a2551f57464295.