1
Ex-GraphRAG: Interpretable Evidence Routing for Graph-Augmented LLMs
新型图增强LLM框架Ex-GraphRAG，通过可解释证据路由解决GNN编码器节点贡献纠缠问题。
arXiv:2605.21994v1 Announce Type: cross Abstract: GraphRAG conditions language models on subgraphs retrieved from knowledge graphs, encoded via messag…