Year: 2026
Type: conference-paper
Abstract: Graph-based retrieval-augmented generation (GraphRAG) is effective for knowledgeintensive and multi-hop query tasks; however, many existing methods primarily seed entitybased graphs and rely on implicit semantic relevance propagation.This often (i) underretrieves when user queries are abstract and semantically sparse at the entity level, and (ii) suffers from brittle multi-hop reasoning, where noisy activations can derail entity-to-entity transitions and corrupt the inferred relation chain, yielding unreliable conclusions.To this end, we propose FlowRAG, a semantic-aware retrieval framework that improves both semantic recall and explicit reasoning.Specifically, FlowRAG constructs a quad-level heterogeneous graph over passages, summaries, sentences, and entities, where summary nodes serve as a coarse semantic hub.At retrieval time, a dual-granularity activation module combines summary-query alignment with sentence-level matching to activate relevant entities under paraphrase and abstraction robustly.We then introduce a frequency-aware weighted flow module that routes relevance through entity-passage links weighted by within-passage term frequency, pruning noisy connections and extracting highconfidence reasoning paths as an explicit logic skeleton for generation.Extensive experiments show that FlowRAG obtains state-of-the-art performance on complex reasoning benchmarks.
Authors: Bihao Zhan, Zongsheng Cao, Jie Zhou, Bo Zhang, Liang He
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Awards: G4966914577, G6250510606, G7864132582
OpenAlex ID: W7166810843