DuoFlow-KG: a dual-modal evidence retrieval framework for high-density LLM-augmented KGQA.

Abstract

Knowledge Graph Question Answering has increasingly adopted a retrieval-reasoning decoupling paradigm, where large language models synthesize answers based on retrieved evidence subgraphs. However, existing retrieval methods often fail to jointly optimize semantic relevance and structural dependencies, resulting in fragmented evidence or search space explosion in multi-hop reasoning. In this work, we propose DuoFlow-KG, a unified dual-modal evidence retrieval framework that constructs compact, high-density evidence subgraphs through integrated structure-semantic modeling. Specifically, we introduce a dual-directional knowledge anchoring strategy that enriches entity representations by incorporating both incoming and outgoing relational neighborhoods with explicit inverse relation injection. A dual-modal fusion module is designed to project semantic resonance and topological distribution into a unified high-dimensional embedding space, where a scalar diffusion mechanism generates structural fingerprints to discriminate textually similar facts based on spatial reachability. Furthermore, we employ a hierarchical weak-supervision scheme, where diversity-aware sampling guided by Maximal Marginal Relevance is used to reduce redundancy and retain reasoning-critical evidence. Extensive experiments on WebQuestionsSP and ComplexWebQuestions benchmarks demonstrate that DuoFlow-KG achieves strong overall performance and best F1, achieving F1 scores of 77.28% and 61.33% respectively. Ablation studies confirm the complementary contributions of semantic modeling, structural reasoning, and bidirectional anchoring, particularly in complex multi-hop scenarios.