MacRAG: Compress, Slice, and Scale-up for Multi-scale Adaptive Context RAG

ACL ARR 2025 May Submission384 Authors

Abstract: Long-context large language models (LC LLMs) combined with retrieval-augmented generation (RAG) hold strong potential for complex multi-hop and large-document tasks. However, existing RAG systems often suffer from imprecise retrieval, incomplete context coverage under constrained windows, and fragmented information from suboptimal context construction. We introduce **Multi-scale Adaptive Context RAG (MacRAG)**, a hierarchical RAG framework that compresses and partitions documents into coarse-to-fine granularities, then adaptively merges relevant contexts through real-time chunk- and document-level expansions. By initiating with finest-level retrieval and progressively incorporating broader, higher-level context, MacRAG constructs effective query-specific long contexts, optimizing both precision and coverage. Evaluations on challenging LongBench expansions of HotpotQA, 2WikiMultihopQA, and Musique confirm MacRAG consistently surpasses baseline RAG pipelines in single- and multi-step generation using Llama-3.1-8B, Gemini-1.5-pro, and GPT-4o. Our results establish MacRAG as an efficient, scalable solution for real-world long-context, multi-hop reasoning.

Paper Type: Long

Research Area: Question Answering

Research Area Keywords: Retrieval-Augmented Generation, Adaptive Retrieval, Long-context Reasoning, Multi-hop QA, Inference Efficiency

Contribution Types: NLP engineering experiment

Languages Studied: English

Submission Number: 384