Auto-Cypher: Improving LLMs on Cypher generation via LLM-supervised generation-verification framework

TL;DR

This paper introduces Auto-Cypher, a framework that uses LLM supervision to generate high-quality Cypher query data, significantly improving LLM performance on Cypher generation tasks for graph databases.

Contribution

The paper presents a novel LLM-supervised pipeline for synthetic Cypher data generation, enhancing the training of LLMs for graph database query translation.

Findings

Generated 29.8k high-quality Cypher instances across domains

Training LLMs on SynthCypher improves performance by up to 40%

Achieved 30% performance gains on the SPIDER benchmark

Abstract

Graph databases like Neo4j are gaining popularity for handling complex, interconnected data, over traditional relational databases in modeling and querying relationships. While translating natural language into SQL queries is well-researched, generating Cypher queries for Neo4j remains relatively underexplored. In this work, we present an automated, LLM-Supervised, pipeline to generate high-quality synthetic data for Text2Cypher. Our Cypher data generation pipeline introduces LLM-As-Database-Filler, a novel strategy for ensuring Cypher query correctness, thus resulting in high quality generations. Using our pipeline, we generate high quality Text2Cypher data - SynthCypher containing 29.8k instances across various domains and queries with varying complexities. Training open-source LLMs like LLaMa-3.1-8B, Mistral-7B, and QWEN-7B on SynthCypher results in performance gains of up to 40% on the Text2Cypher test split and 30% on the SPIDER benchmark, adapted for graph databases.