BubbleRAG enables high-precision retrieval-augmented generation over black-box Knowledge Graphs where the schema and structure are unknown.
March 24, 2026
Original Paper
BubbleRAG: Evidence-Driven Retrieval-Augmented Generation for Black-Box Knowledge Graphs
arXiv · 2603.20309
The Takeaway
Most Graph-RAG methods require pre-defined schemas; BubbleRAG treats retrieval as an Optimal Informative Subgraph problem. It uses heuristic expansion to discover evidence in unknown graphs, significantly improving accuracy on multi-hop QA benchmarks.
From the abstract
Large Language Models (LLMs) exhibit hallucinations in knowledge-intensive tasks. Graph-based retrieval augmented generation (RAG) has emerged as a promising solution, yet existing approaches suffer from fundamental recall and precision limitations when operating over black-box knowledge graphs -- graphs whose schema and structure are unknown in advance. We identify three core challenges that cause recall loss (semantic instantiation uncertainty and structural path uncertainty) and precision los