The Case for Intent-Based Query Rewriting

TL;DR

This paper introduces intent-based query rewriting, allowing queries to be reformulated for better access and privacy, using a system called INQURE that leverages large language models for understanding and rewriting queries.

Contribution

The paper presents INQURE, a novel system for intent-based query rewriting that utilizes large language models to generate alternative queries while maintaining insights.

Findings

INQURE effectively generates alternative queries with comparable insights.

The system performs well across diverse database schemas.

Trade-offs between runtime and rewrite quality are discussed.

Abstract

With this work, we describe the concept of intent-based query rewriting and present a first viable solution. The aim is to allow rewrites to alter the structure and syntactic outcome of an original query while keeping the obtainable insights intact. This drastically differs from traditional query rewriting, which typically aims to decrease query evaluation time by using strict equivalence rules and optimization heuristics on the query plan. Rewriting queries to queries that only provide a similar insight but otherwise can be entirely different can remedy inaccessible original data tables due to access control, privacy, or expensive data access regarding monetary cost or remote access. In this paper, we put forward INQURE, a system designed for INtent-based QUery REwriting. It uses access to a large language model (LLM) for the query understanding and human-like derivation of alternate queries. Around the LLM, INQURE employs upfront table filtering and subsequent candidate rewrite pruning and ranking. We report on the results of an evaluation using a benchmark set of over 900 database table schemas and discuss the pros and cons of alternate approaches regarding runtime and quality of the rewrites of a user study.