DuoFlow-KG: a dual-modal evidence retrieval framework for high-density LLM-augmented KGQA.
This work proposes DuoFlow-KG, a unified dual-modal evidence retrieval framework that constructs compact, high-density evidence subgraphs through integrated structure-semantic modeling and introduces a dual-directional knowledge anchoring strategy that enriches entity representations by incorporating both incoming and outgoing relational neighborhoods with explicit inverse relation injection.