# Query-Aware Spreading Activation for Multi-Hop Retrieval over Knowledge Graphs Source: [Query-Aware Spreading Activation for Multi-Hop Retrieval over Knowledge Graphs]() Collection index: [llms.txt]() Data updated: 2026-07-01T05:00:18.486Z Authors: Illia Makarov, Mykola Glybovets Published: 2026-06-29T11:10:19.000Z ## Abstract Retrieval-augmented generation built on knowledge graphs (Graph RAG) outperforms flat passage retrieval on multi-hop question answering by leveraging graph structure. In most existing systems, however, the question only sets the seed nodes; the subsequent traversal becomes "query-blind", depending solely on the graph structure. The exception is QAFD-RAG, which implements query-aware traversal via a flow-diffusion solver with combined edge re-weighting. This architecture requires loading the full graph into Python memory and an iterative solver with a variable number of iterations complicating integration with the graph database. We propose a spreading-activation method that achieves the same query-aware traversal with a single per-step semantic gate: the step weight is the cosine similarity between the candidate entity's description and the question, and the number of iterations is fixed. The whole retrieval procedure - seed mapping, propagation, top-K selection and context assembly - is expressed as a single Cypher query executed in one round-trip to Neo4j; the graph never leaves the database. On MuSiQue our method matches QAFD-RAG by exact match (32.80 vs 33.50) and outperforms the strongest purely-structural baseline in our comparison, HippoRAG, by 5.3 EM and 3.4 F1; on 2WikiMultiHopQA HippoRAG and QAFD-RAG retain an advantage due to their phrase-node architectures. An ablation with the gate disabled confirms that the gate is the source of a simultaneous F1 gain of 3.6 to 7.4 points and a retrieval-latency reduction by a factor of 1.5 to 4.9. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Multi-hop Question Answering on MuSiQue n=1,000 samples (test)](): Multi-hop Question Answering; MuSiQue n=1,000 samples (test); F1 Score: 41.68. - [Multi-hop Question Answering on 2WikiMultiHopQA n=1,000 samples (test)](): Multi-hop Question Answering; 2WikiMultiHopQA n=1,000 samples (test); F1 Score: 55. ## Original sources and implementation [Original paper]() [PDF]()