P$^2$RAG: Efficient Privacy-Preserving RAG Service Supporting Arbitrary Top-$k$ Retrieval 事件

P$^2$RAG: Efficient Privacy-Preserving RAG Service Supporting Arbitrary Top-$k$ Retrieval arXiv:2603.14778v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) enables large language models to use external knowledge, but outsourcing the RAG service raises privacy concerns for both data owners and users. Privacy-preserving RAG systems address these concerns by performing secure top-$k$ retrieval, which is typically implemented using secure sorting to identify relevant do