arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.01763cs.DBcs.AIcs.CLcs.LG
收藏

当大语言模型遇见向量数据库:一项综述

When Large Language Models Meet Vector Databases: A Survey

Carnegie Mellon University(卡内基梅隆大学);Purdue University(普渡大学);University of Michigan(密歇根大学);Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳));National Science Library (Chengdu), Chinese Academy of Sciences(中国科学院成都科学图书馆);Shandong University of Technology(山东科技大学)

Zhi Jing, Yongye Su, Yikun Han, Bo Yuan, Haiyun Xu, Chunjiang Liu, Kehai Chen, Min Zhang

AI总结:

本文综述大语言模型与向量数据库的协同作用,分析向量数据库如何缓解幻觉、知识过时等问题,并展望未来研究方向以增强数据处理与知识提取能力。

摘要:

本综述探讨了大语言模型(LLMs)与向量数据库(VecDBs)之间的协同潜力,这是一个新兴但快速发展的研究领域。随着大语言模型的普及,一系列挑战随之而来,包括幻觉、知识过时、高昂的商业应用成本以及内存问题。向量数据库通过提供一种高效的手段来存储、检索和管理大语言模型操作中固有的高维向量表示,成为解决这些问题的有力方案。通过这次细致的回顾,我们阐述了大语言模型和向量数据库的基础原理,并批判性地分析了它们的集成对增强大语言模型功能的影响。本文的讨论还延伸至对该领域推测性未来发展的探讨,旨在促进进一步研究,以优化大语言模型与向量数据库的融合,实现先进的数据处理和知识提取能力。

英文摘要:

This survey explores the synergistic potential of Large Language Models (LLMs) and Vector Databases (VecDBs), a burgeoning but rapidly evolving research area. With the proliferation of LLMs comes a host of challenges, including hallucinations, outdated knowledge, prohibitive commercial application costs, and memory issues. VecDBs emerge as a compelling solution to these issues by offering an efficient means to store, retrieve, and manage the high-dimensional vector representations intrinsic to LLM operations. Through this nuanced review, we delineate the foundational principles of LLMs and VecDBs and critically analyze their integration's impact on enhancing LLM functionalities. This discourse extends into a discussion on the speculative future developments in this domain, aiming to catalyze further research into optimizing the confluence of LLMs and VecDBs for advanced data handling and knowledge extraction capabilities.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑