@inproceedings{tiwari-etal-2025-auto,
    title = "Auto-Cypher: Improving {LLM}s on Cypher generation via {LLM}-supervised generation-verification framework",
    author = "Tiwari, Aman  and
      Malay, Shiva Krishna Reddy  and
      Yadav, Vikas  and
      Hashemi, Masoud  and
      Madhusudhan, Sathwik Tejaswi",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.naacl-short.53/",
    pages = "623--640",
    ISBN = "979-8-89176-190-2",
    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 QWEN7B 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."
}