STAR: Semantic-Tuned and Tail-Adaptive Retriever for Graph-Augmented Generation

ArXi:2605.18765v1 Announce Type: cross To augment Large Language Models (LLMs) for multi-hop question answering, a mainstream solution within Graph Retrieval Augmented Generation (GraphRAG) leverages lightweight retrievers to efficiently extract information from a given Knowledge Graph (KG). However, existing methods often overlook the inherent challenge of sparse semantic information in graphs.