VeriCypher：通过 Text-to-Cypher 生成实现 GraphRAG 的命名实体校验

View PDF HTML (experimental)

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.

Comments:	this https URL
Subjects:	Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
MSC classes:	68P20, 68T30
ACM classes:	I.2.7; I.2.11; H.2.4
Cite as:	arXiv:2511.08274 [cs.AI]
	(or arXiv:2511.08274v2 [cs.AI] for this version)
	https://doi.org/10.48550/arXiv.2511.08274 arXiv-issued DOI via DataCite

Submission history

From: Anton Gusarov [view email]
[v1] Tue, 11 Nov 2025 14:04:00 UTC (532 KB)
[v2] Sun, 1 Nov 2026 22:38:31 UTC (1,479 KB)