AI 大模型

RAG / 检索增强生成

检索增强生成、向量检索、知识库问答和面向大模型的搜索系统。

2026-09-01 至 2026-09-01 共收录 3 篇信号源：cs.IR, cs.CL, cs.AI, cs.DB

1. 向量检索 3 篇

2608.28766 2026-09-01 cs.SE 新提交 93%

Beyond Vector Search: Comparing Classical RAG with Hybrid GraphRAG for Climate Science Q\&A

超越向量搜索：对比经典RAG与混合GraphRAG在气候科学问答中的表现

Daniel Naiff, Ronnie Alves, Gustavo Pinto

专题命中向量检索：RAG(title,title_cn)；vector search(title,abstract)；retrieval-augmented generation(abstract)

AI总结针对传统RAG无法捕捉科学语料概念层级关系的问题，提出整合向量搜索、GraphRAG等的混合架构，在气候科学问答中相比经典RAG实现相关性与召回率大幅提升，为分散科学文献的高效问答系统提供新方向。

Comments 9 pages

Journal ref ENIAC 2026

2509.08395 2026-09-01 cs.DB 版本更新 81%

SINDI: An Efficient Index for Sparse Vector Approximate Maximum Inner Product Search

SINDI：一种高效的近似最大内积搜索索引

Ruoxuan Li, Xiaoyao Zhong, Jiabao Jin, Peng Cheng, Wangze Ni, Zhitao Shen, Wei Jia, Xiangyu Wang, Heng Tao Shen, Jingkuan Song

专题命中向量检索：RAG(abstract,abstract_cn)；retrieval-augmented generation(abstract)；vector search(abstract)；分类 cs.DB

AI总结 SINDI通过高效内积计算、内存友好设计和向量修剪，提升了稀疏向量近似最大内积搜索的效率和性能。

Comments 18 pages, accepted by ICDE 2026. Due to submission limitation for ICDE 2026 (i.e., maximum 6 submissions per author), Lei Chen and Xuemin Lin are not included as authors

2503.12896 2026-09-01 cs.CR 版本更新 75%

Privacy-Preserving LLM Embedding Transmission for End-Cloud Collaboration

面向端云协同的隐私保护大语言模型嵌入传输

Shuaifan Jin, Xiaoyi Pang, Zhibo Wang, He Wang, Jiacheng Du, Jiahui Hu, Kui Ren

专题命中向量检索：RAG(abstract,abstract_cn)；retrieval-augmented generation(abstract)

AI总结本文针对端云协同中嵌入反转攻击导致的隐私泄露问题，提出基于熵扰动的EntroGuard方法，可在保护嵌入隐私的同时维持检索性能，且无需修改嵌入模型。

Comments Accepted for publication in IEEE Transactions on Networking. This is the Author Accepted Manuscript