fastbmRAG: A Fast Graph-Based RAG Framework for Efficient Processing of Large-Scale Biomedical Literature

TL;DR

fastbmRAG is a novel, efficient graph-based retrieval-augmented generation framework that significantly speeds up processing of large-scale biomedical literature while maintaining high accuracy and coverage.

Contribution

introduces fastbmRAG, a two-stage graph construction method that reduces computational load and accelerates biomedical literature analysis for LLM applications.

Findings

over 10x faster than existing tools

achieves superior coverage and accuracy

effective for large-scale biomedical literature understanding

Abstract

Large language models (LLMs) are rapidly transforming various domains, including biomedicine and healthcare, and demonstrate remarkable potential from scientific research to new drug discovery. Graph-based retrieval-augmented generation (RAG) systems, as a useful application of LLMs, can improve contextual reasoning through structured entity and relationship identification from long-context knowledge, e.g. biomedical literature. Even though many advantages over naive RAGs, most of graph-based RAGs are computationally intensive, which limits their application to large-scale dataset. To address this issue, we introduce fastbmRAG, an fast graph-based RAG optimized for biomedical literature. Utilizing well organized structure of biomedical papers, fastbmRAG divides the construction of knowledge graph into two stages, first drafting graphs using abstracts; and second, refining them using main texts guided by vector-based entity linking, which minimizes redundancy and computational load. Our evaluations demonstrate that fastbmRAG is over 10x faster than existing graph-RAG tools and achieve superior coverage and accuracy to input knowledge. FastbmRAG provides a fast solution for quickly understanding, summarizing, and answering questions about biomedical literature on a large scale. FastbmRAG is public available in https://github.com/menggf/fastbmRAG.