Prompting large language models based on semantic schema for text-to-Cypher transformation towards domain Q&A
Decision Support Systems · 2025-12 · 199 · 114553
DOI: 10.1016/j.dss.2025.114553 ↗Kurz gefasst
Fachartikel in der Zeitschrift Decision Support Systems, 2025-12. Verfasst von Yuwei Wan und 4 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Translating natural language inquiries into executable Cypher queries (text-to-Cypher) is a persistent bottleneck for non-technical teams relying on knowledge graphs (KGs) in fast-changing industrial settings. Rule and template converters need frequent updates as schemas evolve, while supervised and fine-tuned parsers require recurring training. This study proposes a schema-guided prompting approach, namely text-to-Cypher with semantic schema (T2CSS), to align large language models (LLMs) with domain knowledge for producing accurate Cypher. T2CSS distils a domain ontology into a lightweight semantic schema and uses adaptive filtering to inject the relevant subgraph and essential Cypher rules into the prompt for constraining generation and reducing schema-agnostic errors. This design keeps the prompt focused and within context length limits while providing the necessary domain grounding. Comparative experiments demonstrate that T2CSS with GPT-4 outperformed baseline models and achieved 86 % accuracy in producing correct Cypher queries. In practice, this study reduces retraining and maintenance effort, shortens turnaround times, and broadens KG access for non-experts.
Zitieren
APA
Wan, Y., Chen, Z., Liu, Y., Chen, C., & Packianather, M. (2025). Prompting large language models based on semantic schema for text-to-Cypher transformation towards domain Q&A. Decision Support Systems, 199, 114553. https://doi.org/10.1016/j.dss.2025.114553
Vancouver
Wan Y, Chen Z, Liu Y, Chen C, Packianather M. Prompting large language models based on semantic schema for text-to-Cypher transformation towards domain Q&A. Decision Support Systems. 2025;199:114553. doi:10.1016/j.dss.2025.114553
BibTeX
@article{Wan2025,
author = {Wan, Yuwei and Chen, Zheyuan and Liu, Ying and Chen, Chong and Packianather, Michael},
title = {Prompting large language models based on semantic schema for text-to-Cypher transformation towards domain Q&A},
journal = {Decision Support Systems},
year = {2025},
volume = {199},
pages = {114553},
doi = {10.1016/j.dss.2025.114553}
}
EUVIMED