这个领域收两篇：一篇用社区摘要做全局意义建构，一篇用知识原子化做多跳推理。页首是摘要和总结的翻译，PDF 收在下面的组件里。

• From Local to Global: A Graph RAG Approach to Query-Focused Summarization
• PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation

版权所有

版权归属：Pray0

许可证：署名 4.0 国际 (CC-BY-4.0)

下一页From Local to Global: A Graph RAG Approach to Query-Focused Summarization