BubbleRAG: Evidence-Driven Retrieval-Augmented Generation for Black-Box Knowledge Graphs
This addresses recall and precision limitations in graph-based RAG for black-box knowledge graphs, offering a plug-and-play solution for knowledge-intensive tasks.
The paper tackles the problem of hallucinations in LLMs for knowledge-intensive tasks by proposing BubbleRAG, a retrieval-augmented generation method for black-box knowledge graphs, achieving state-of-the-art results on multi-hop QA benchmarks with improved F1 and accuracy.
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 loss (evidential comparison uncertainty). To address these challenges, we formalize the retrieval task as the Optimal Informative Subgraph Retrieval (OISR) problem -- a variant of Group Steiner Tree -- and prove it to be NP-hard and APX-hard. We propose BubbleRAG, a training-free pipeline that systematically optimizes for both recall and precision through semantic anchor grouping, heuristic bubble expansion to discover candidate evidence graphs (CEGs), composite ranking, and reasoning-aware expansion. Experiments on multi-hop QA benchmarks demonstrate that BubbleRAG achieves state-of-the-art results, outperforming strong baselines in both F1 and accuracy while remaining plug-and-play.