cs.AINov 11, 2025

VeriCypher: Named-Entity Verification for GraphRAG via Text-to-Cypher Generation

Authors: Anton Gusarov, Anastasia Volkova, Valentin Khrulkov, Andrey Kuznetsov, Evgenii Maslov, Ivan Oseledets

Organizations: 1AIRI · 2Skoltech · Innopolis University

Abstract

Knowledge graph question answering has traditionally focused on Resource Description Framework (RDF) graphs, SPARQL queries, and triple-based representations. Labeled Property Graphs (LPGs), however, pose a different challenge for LLM-based query generation: executable Cypher queries must align with schema structure, traversal direction, property keys, and literal entity values. This motivated us to introduce VeriCypher, an LLM-based text-to-Cypher framework for question answering over LPGs. It combines query generation conditioned on Cypher-like graph schema summaries with runtime execution, LLM-based query evaluation, and iterative correction where the central mechanism is named-entity verification: the system extracts node labels, relationship patterns, property keys, and literal values from generated queries, checks them against the target graph and schema, and turns mismatches into correction instructions for the next generation step. We evaluate VeriCypher on the CypherBench benchmark across multiple domains and LLM backbones. Compared with an LLM baseline, this method consistently improves answer correctness and query robustness. Ablation results further show that named-entity verification helps correct hallucinated schema elements and entity values, supporting more reliable LLM-based question answering over heterogeneous property graphs.

Figures & tables

Explore similar work

CardsList
  1. KG2Cypher: Data-Centric Pipeline for Building Enterprise Text-to-Cypher Systems

    Jun 26, 2026Minjun Choi, Yerin Kim, Junghyuk Seo +3Text-to-CypherKnowledge Graph Question Answering

  2. Graph Query Generation with Constraint-guided Large Language Agents

    Apr 9, 2026Mengying Wang, Nicolaas Jedema, Rahul Pandey +3Knowledge Graph Question AnsweringLLM Agents

  3. PIPE-Cypher: Automatic Enterprise Benchmark Generation for Text-to-Cypher Systems

    Jun 7, 2026Suraj Ranganath, Anish RaghavendraBenchmark DesignText-to-Cypher