SVD-RAG: Efficient Tree-Organized Retrieval-Augmented Generation via Singular Value Decomposition

Jul 14, 2026

SVD-RAG introduces the use of Singular Value Decomposition (SVD) on dense sentence embeddings for extractive summarization in hierarchical Retrieval-Augmented Generation (RAG) systems, replacing the need for expensive LLM-based summarization. The method achieves retrieval quality within 1-5% of RAPTOR while constructing the retrieval tree 317 times faster and reducing token consumption by approximately 85%. SVD-RAG is deterministic, cost-efficient, and adapts to content complexity automatically.

Why it matters: This approach makes hierarchical RAG systems significantly more practical and scalable by reducing computational cost and latency without substantially sacrificing retrieval quality.

Full story at: arXiv Information Retrieval ↗