This work proposes \ourmethod, a unified end-to-end GraphRAG framework that tightly couples a GFM retriever with an LLM generator and introduces a semantic-guided distillation module that provides auxiliary supervision using pseudo-labels derived from query-document semantic similarities.
Zi-Cheng Zhao, Lin-Hao Luo, Zong-Ji Yu et al.· 0 citations
This work proposes HyperReCo, a framework for retrieving and connecting evidence with a hypergraph neural network (HyperGNN), and introduces Gradient-Guided Hyper-Path Decoding (GGHD), which uses gradient attribution to interpret the learned interactions and translate them into explicit hyper-paths that help LLMs combi...
Zi-Cheng Zhao, Lin-Hao Luo, Jun-Nan Dong et al.· 0 citations
LADDER is a novel framework that bridges diffusion language modeling with GraphRAG through graph-guided parallel decoding through graph-guided parallel decoding, and proposes an event-driven self-clocking retrieval, inspired by the key insight that 88% of target entities emerge early in the partially denoised state.
This work formalizes a Wiki Graph schema that seamlessly bridges fine-grained structures with dense contexts, maintaining explicit topologies alongside continuous semantics and engineer an infrastructural NCCL boundary exchange protocol that hoists static partition indices and leverages fixed-shape GPU-to-GPU collectiv...