Routing End User Queries to Enterprise Databases

TL;DR

This paper presents a reasoning-based reranking approach for routing natural language queries to the correct enterprise databases, addressing challenges posed by large, overlapping schemas and ambiguous queries, and demonstrating superior performance over baseline methods.

Contribution

It introduces a modular, reasoning-driven reranking strategy that explicitly models schema coverage, structural connectivity, and semantic alignment, improving query routing accuracy.

Findings

Outperforms embedding-only and LLM prompting baselines across metrics

Effective in large, domain-overlapping database environments

Addresses ambiguity in natural language queries

Abstract

We address the task of routing natural language queries in multi-database enterprise environments. We construct realistic benchmarks by extending existing NL-to-SQL datasets. Our study shows that routing becomes increasingly challenging with larger, domain-overlapping DB repositories and ambiguous queries, motivating the need for more structured and robust reasoning-based solutions. By explicitly modelling schema coverage, structural connectivity, and fine-grained semantic alignment, the proposed modular, reasoning-driven reranking strategy consistently outperforms embedding-only and direct LLM-prompting baselines across all the metrics.