arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2411.01807cs.DBcs.AI
收藏

语言模型能否实现上下文数据库?

Can Language Models Enable In-Context Database?

University of Nebraska-Lincoln(内布拉斯加大学林肯分校);East Carolina University(东卡罗来纳大学)

Yu Pan, Hongfeng Yu, Tianjiao Zhao, Jianxin Sun

AI总结:

本文提出数据库增量编码方法,将传统RDBMS数据编码为上下文文本,使LLMs支持动态更新的上下文数据库,并通过基准InConDB评估其CRUD操作能力,揭示性能与局限。

摘要:

大型语言模型(LLMs)正逐渐成为能够处理多种任务的少样本学习者,这些任务包括理解、规划、推理、问答、算术计算等。这些能力的核心在于LLMs在表示和理解结构化或半结构化数据(如表格和图)方面的熟练程度。大量研究表明,在表格数据或图上进行推理不仅对LLMs可行,而且开辟了一个有前景的研究方向,即将这些数据视为上下文数据。上下文数据库的轻量级和人类可读的特性,使其有可能在典型的RAG(检索增强生成)设置中成为传统数据库的替代方案。然而,目前几乎所有的工作都集中在静态的上下文数据上,这不允许动态更新。在本文中,为了实现数据库的动态更新,我们提出了数据库的增量编码。我们探索了如何将存储在传统关系数据库管理系统(RDBMS)中的数据编码为上下文文本,并评估LLMs对上下文数据库执行CRUD(创建、读取、更新和删除)操作的能力。我们提出了一个名为InConDB的基准,并进行了大量实验,通过改变数据库编码方法、提示方法、操作类型和输入数据分布,展示了不同语言模型在实现上下文数据库方面的性能,揭示了其能力和局限性。

英文摘要:

Large language models (LLMs) are emerging as few-shot learners capable of handling a variety of tasks, including comprehension, planning, reasoning, question answering, arithmetic calculations, and more. At the core of these capabilities is LLMs' proficiency in representing and understanding structural or semi-structural data, such as tables and graphs. Numerous studies have demonstrated that reasoning on tabular data or graphs is not only feasible for LLMs but also gives a promising research direction which treats these data as in-context data. The lightweight and human readable characteristics of in-context database can potentially make it an alternative for the traditional database in typical RAG (Retrieval Augmented Generation) settings. However, almost all current work focuses on static in-context data, which does not allow dynamic update. In this paper, to enable dynamic database update, delta encoding of database is proposed. We explore how data stored in traditional RDBMS can be encoded as in-context text and evaluate LLMs' proficiency for CRUD (Create, Read, Update and Delete) operations on in-context databases. A benchmark named InConDB is presented and extensive experiments are conducted to show the performance of different language models in enabling in-context database by varying the database encoding method, prompting method, operation type and input data distribution, revealing both the proficiency and limitations.

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。

↑