AdaComp: Extractive Context Compression with Adaptive Predictor for Retrieval-Augmented Large Language Models

ArXi:2409.01579v2 Announce Type: replace-cross Retrieved documents containing noise will hinder RAG from detecting answer clues and make the inference process slow and expensive. Therefore, context compression is necessary to enhance its accuracy and efficiency. Existing context compression methods use extractive or generative models to retain the most query-relevant sentences or apply the information bottleneck theory to preserve sufficient information. However, these methods may face issues such as over-compression or high computational costs.