Toward Multi-Database Query Reasoning for Text2Cypher

TL;DR

This paper introduces a structured approach to enable large language models to reason across multiple graph databases for natural language query translation, addressing real-world distributed data scenarios.

Contribution

It formalizes the multi-database reasoning problem for Text2Cypher, proposing a three-phase roadmap for database routing, decomposition, and heterogeneous query reasoning.

Findings

Formalization of multi-database reasoning for Text2Cypher

Identification of challenges in source selection and query decomposition

Roadmap for future research in multi-database natural language interfaces

Abstract

Large language models have significantly improved natural language interfaces to databases by translating user questions into executable queries. In particular, Text2Cypher focuses on generating Cypher queries for graph databases, enabling users to access graph data without query language expertise. Most existing Text2Cypher systems assume a single preselected graph database, where queries are generated over a known schema. However, real-world systems are often distributed across multiple independent graph databases organized by domain or system boundaries, where relevant information may span multiple sources. To address this limitation, we propose a shift from single-database query generation to multi-database query reasoning. Instead of assuming a fixed execution context, the system must reason about (i) relevant databases, (ii) how to decompose a question across them, and (iii) how to integrate partial results. We formalize this setting through a three-phase roadmap: database routing, multi-database decomposition, and heterogeneous query reasoning across database types and query languages. This work provides a structured formulation of multi-database reasoning for Text2Cypher and identifies challenges in source selection, query decomposition, and result integration, aiming to support more realistic and scalable natural language interfaces to graph databases.