Can Language Models Enable In-Context Database?

TL;DR

This paper investigates using large language models as dynamic in-context databases capable of CRUD operations, proposing delta encoding for updates and evaluating performance with a new benchmark.

Contribution

It introduces delta encoding for dynamic in-context databases and evaluates LLMs' ability to perform CRUD operations on encoded data.

Findings

LLMs can perform CRUD operations on in-context databases.

Delta encoding enables dynamic updates in in-context data.

Performance varies with encoding, prompting, and data distribution.

Abstract

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.