RAG / 检索增强生成

Fast Tuning the Index Construction Parameters of Proximity Graphs in Vector Databases

向量数据库中接近图索引构造参数的快速调整

Wenyang Zhou, Jiadong Xie, Yingfan Liu, Zhihao Yin, Jeffrey Xu Yu, Hui Li, Zhangqian Mu, Xiaotian Qiao, Jiangtao Cui

专题命中 向量检索 ：retrieval-augmented generation(abstract)；分类 cs.DB

AI总结 本文提出FastPGT框架，通过同时构建多个接近图以加速参数调整，显著提升向量数据库中接近图构造参数优化的效率。

Physically Interpretable AlphaEarth Foundation Model Embeddings Enable LLM-Based Land Surface Intelligence

可解释的AlphaEarth基础模型嵌入使基于大语言模型的地表智能成为可能

Mashrekur Rahman

机构 * Dartmouth College（达特茅斯学院） 纠错

专题命中 向量检索 ：retrieval-augmented generation(abstract)；分类 cs.CL

AI总结 基于AlphaEarth基础模型的可解释嵌入，通过检索增强生成实现地表智能，验证了卫星嵌入在环境决策中的有效性。

Scaling Laws for Embedding Dimension in Information Retrieval

信息检索中嵌入维度的缩放规律

Julian Killingback, Mahta Rafiee, Madine Manas, Hamed Zamani

机构 * Center for Intelligent Information Retrieval（智能信息检索中心） ； University of Massachusetts Amherst（马萨诸塞大学阿姆赫斯特分校） 纠错

专题命中 向量检索 ：dense retrieval(abstract)；分类 cs.IR

AI总结 本研究分析了嵌入维度与检索性能之间的缩放关系，发现性能随嵌入维度增加而改善，但存在边际效益递减，同时提出基于嵌入维度和模型规模的联合缩放规律。

Comments 9 Pages, 7 figures

Beyond Cosine Similarity: Taming Semantic Drift and Antonym Intrusion in a 15-Million Node Turkish Synonym Graph

超越余弦相似度：在1500万个节点的土耳其同义词图中驯服语义漂移和反义入侵

Ebubekir Tosun, Mehmet Emin Buldur, Özay Ezerceli, Mahmoud ElHussieni

专题命中 向量检索 ：retrieval-augmented generation(abstract)；分类 cs.CL

AI总结 本文提出了一种基于三元语义关系判别器和软到硬聚类算法的语义聚类系统，有效解决同义词与反义词区分问题，提升语义检索精度。

CoRECT: A Framework for Evaluating Embedding Compression Techniques at Scale

CoRECT：大规模评估嵌入压缩技术的框架

L. Caspari, M. Dinzinger, K. Ghosh Dastidar, C. Fellicious, J. Mitrović, M. Granitzer

专题命中 向量检索 ：dense retrieval(abstract)；分类 cs.IR

AI总结 CoRECT框架通过大规模评估和新数据集，展示非学习压缩在减少索引大小的同时保持性能，为压缩方法的选择提供一致比较依据。

Distribution-Aware Exploration for Adaptive HNSW Search

面向分布的探索：自适应HNSW搜索

Chao Zhang, Renée J. Miller

专题命中 向量检索 ：vector search(abstract)；分类 cs.DB

AI总结 本文提出Ada-ef方法，通过动态配置ef实现高效近邻搜索，减少查询延迟和计算资源消耗。

Comments Accepted for publication in SIGMOD 2026

Continuous Prompts: LLM-Augmented Pipeline Processing over Unstructured Streams

连续提示：基于大语言模型的流处理管道处理

Shu Chen, Deepti Raghavan, Uğur Çetintemel

专题命中 向量检索 ：RAG(abstract)；分类 cs.DB

AI总结 本文提出连续提示框架，通过引入大语言模型的持续推理能力，实现对无结构流的持久语义处理，并通过动态优化提升效率与精度的平衡。

Exploring Distributed Vector Databases Performance on HPC Platforms: A Study with Qdrant

Seth Ockerman, Amal Gueroudji, Song Young Oh, Robert Underwood, Nicholas Chia, Kyle Chard, Robert Ross, Shivaram Venkataraman

专题命中 向量检索 ：retrieval-augmented generation(abstract)；分类 cs.DB

Comments To appear in the SC'25 Workshop Frontiers in Generative AI for HPC Science and Engineering: Foundations, Challenges, and Opportunities

HAKES: Scalable Vector Database for Embedding Search Service

Guoyu Hu, Shaofeng Cai, Tien Tuan Anh Dinh, Zhongle Xie, Cong Yue, Gang Chen, Beng Chin Ooi

机构 * National University of Singapore（国立新加坡大学） ； Deakin University（德肯大学） ； Zhejiang University（浙江大学） 纠错

专题命中 向量检索 ：retrieval-augmented generation(abstract)；分类 cs.DB

Journal ref PVLDB, 18(9): 3049 - 3062, 2025

DISTRIBUTEDANN: Efficient Scaling of a Single DISKANN Graph Across Thousands of Computers

Philip Adams, Menghao Li, Shi Zhang, Li Tan, Qi Chen, Mingqin Li, Zengzhong Li, Knut Risvik, Harsha Vardhan Simhadri

专题命中 向量检索 ：vector search(abstract)；分类 cs.IR

Efficient Patent Searching Using Graph Transformers

Krzysztof Daniell, Igor Buzhinsky, Sebastian Björkqvist

专题命中 向量检索 ：dense retrieval(abstract)；分类 cs.IR

Comments Accepted for publication at the PatentSemTech 2025 workshop, held in conjunction with SIGIR 2025

Fast and Scalable Gene Embedding Search: A Comparative Study of FAISS and ScaNN

Mohammad Saleh Refahi, Gavin Hearne, Harrison Muller, Kieran Lynch, Bahrad A. Sokhansanj, James R. Brown, Gail Rosen

机构 * Department of Electrical and Computer Engineering, Drexel University, Philadelphia, USA（电气与计算机工程系，德雷塞尔大学，费城，美国） 纠错

专题命中 向量检索 ：vector search(abstract)；分类 cs.AI

Journal ref GenBio @ ICML 2025 Workshop, OpenReview, June 2025 GenBio @ ICML 2025 Workshop, OpenReview, June 2025

Approximate Vector Set Search Inspired by Fly Olfactory Neural System

Yiqi Li, Sheng Wang, Zhiyu Chen, Shangfeng Chen, Zhiyong Peng

专题命中 向量检索 ：vector search(abstract)；分类 cs.DB

LGAI-EMBEDDING-Preview Technical Report

Jooyoung Choi, Hyun Kim, Hansol Jang, Changwook Jun, Kyunghoon Bae, Hyewon Choi, Stanley Jungkyu Choi, Honglak Lee, Chulmin Yun

机构 * LG AI Research（LG人工智能研究） 纠错

专题命中 向量检索 ：retriever(abstract)；分类 cs.CL

Comments 10 pages

GLoSS: Generative Language Models with Semantic Search for Sequential Recommendation

Krishna Acharya, Aleksandr V. Petrov, Juba Ziani

专题命中 向量检索 ：dense retrieval(abstract)；分类 cs.IR

Comments Our code and model checkpoints are publicly available at:https://github.com/krishnacharya/GLoSS

The Impacts of Data, Ordering, and Intrinsic Dimensionality on Recall in Hierarchical Navigable Small Worlds

Owen Pendrigh Elliott, Jesse Clark

专题命中 向量检索 ：vector search(abstract)；分类 cs.IR

Comments 15 pages, 2 figures

Inference-time sparse attention with asymmetric indexing

Pierre-Emmanuel Mazaré, Gergely Szilvasy, Maria Lomeli, Francisco Massa, Naila Murray, Hervé Jégou, Matthijs Douze

机构 * FAIR at Meta（Meta 的 FAIR） 纠错

专题命中 向量检索 ：vector search(abstract)；分类 cs.CL

VecFlow: A High-Performance Vector Data Management System for Filtered-Search on GPUs

Jingyi Xi, Chenghao Mo, Benjamin Karsin, Artem Chirkin, Mingqin Li, Minjia Zhang

专题命中 向量检索 ：vector search(abstract)；分类 cs.DB

Birdie: Natural Language-Driven Table Discovery Using Differentiable Search Index

Yuxiang Guo, Zhonghao Hu, Yuren Mao, Baihua Zheng, Yunjun Gao, Mingwei Zhou

专题命中 向量检索 ：vector search(abstract)；分类 cs.DB

Comments Accepted by VLDB 2025

Embedding Method for Knowledge Graph with Densely Defined Ontology

Takanori Ugai

专题命中 向量检索 ：knowledge retrieval(abstract)；分类 cs.AI

Comments 6pages, 4 figures

Adversarial Decoding: Generating Readable Documents for Adversarial Objectives

Collin Zhang, Tingwei Zhang, Vitaly Shmatikov

专题命中 向量检索 ：RAG(abstract)；分类 cs.CL

SoftMatcha: A Soft and Fast Pattern Matcher for Billion-Scale Corpus Searches

Hiroyuki Deguchi, Go Kamoda, Yusuke Matsushita, Chihiro Taguchi, Kohei Suenaga, Masaki Waga, Sho Yokoi

专题命中 向量检索 ：vector search(abstract)；分类 cs.CL

Comments Accepted at ICLR2025

Representing Signs as Signs: One-Shot ISLR to Facilitate Functional Sign Language Technologies

Toon Vandendriessche, Mathieu De Coster, Annelies Lejon, Joni Dambre

专题命中 向量检索 ：vector search(abstract)；分类 cs.CL

In-Place Updates of a Graph Index for Streaming Approximate Nearest Neighbor Search

Haike Xu, Magdalen Dobson Manohar, Philip A. Bernstein, Badrish Chandramouli, Richard Wen, Harsha Vardhan Simhadri

专题命中 向量检索 ：RAG(abstract)；分类 cs.IR

Revisiting the Index Construction of Proximity Graph-Based Approximate Nearest Neighbor Search

Shuo Yang, Jiadong Xie, Yingfan Liu, Jeffrey Xu Yu, Xiyue Gao, Qianru Wang, Yanguo Peng, Jiangtao Cui

专题命中 向量检索 ：retrieval-augmented generation(abstract)；分类 cs.DB

Comments The paper has been accepted by PVLDB 2025

SQUASH: Serverless and Distributed Quantization-based Attributed Vector Similarity Search

Joe Oakley, Hakan Ferhatosmanoglu

专题命中 向量检索 ：vector search(abstract)；分类 cs.DB

KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model

Xinshuo Hu, Zifei Shan, Xinping Zhao, Zetian Sun, Zhenyu Liu, Dongfang Li, Shaolin Ye, Xinyuan Wei, Qian Chen, Baotian Hu, Haofen Wang, Jun Yu, Min Zhang

专题命中 向量检索 ：retrieval-augmented generation(abstract)；分类 cs.CL

Comments Technical Report. 23 pages, 6 figures, 10 tables

A Primer on Word Embeddings: AI Techniques for Text Analysis in Social Work

Brian E. Perron, Kelley A. Rivenburgh, Bryan G. Victor, Zia Qi, Hui Luan

专题命中 向量检索 ：retrieval augmented generation(abstract)；分类 cs.CL

Comments 37 pages, 3 figures

A Real-Time Adaptive Multi-Stream GPU System for Online Approximate Nearest Neighborhood Search

Yiping Sun, Yang Shi, Jiaolong Du

专题命中 向量检索 ：retrieval-augmented generation(abstract)；分类 cs.IR

Comments Accepted by CIKM'24, V2 fixes some typos

Efficient and Effective Retrieval of Dense-Sparse Hybrid Vectors using Graph-based Approximate Nearest Neighbor Search

Haoyu Zhang, Jun Liu, Zhenhua Zhu, Shulin Zeng, Maojia Sheng, Tao Yang, Guohao Dai, Yu Wang

专题命中 向量检索 ：vector search(abstract)；分类 cs.IR

Comments 8 pages