Improving Cypher Query Generation from Natural Language using Reinforcement Learning with Large Language Models Pekiştirmeli Ö?grenme ve Büyük Dil Modelleri Kullanarak Do?gal Dilden Cypher Sorgusu Üretiminin ?Iyileştirilmesi
34th Signal Processing and Communications Applications Conference, SIU 2026, İstanbul, Turkey, 7 - 10 July 2026, (Full Text)
- Publication Type: Conference Paper / Full Text
- Doi Number: 10.1109/siu71813.2026.11637051
- City: İstanbul
- Country: Turkey
- Keywords: Cypher, Graph Databases, Large Language Models, Natural Language Processing, Reinforcement Learning
- Middle East Technical University Affiliated: Yes
Abstract
This study addresses the automated generation of Cypher queries from natural language expressions for graph databases, systematically analyzing the impact of various training strategies and data augmentation techniques on model performance. Although Large Language Models (LLMs) demonstrate significant potential in natural language-to-query tasks, their generalization to unseen schemas and structural accuracy remain critical challenges. In this context, the study investigates the contributions of Supervised Fine-Tuning (SFT), Reinforcement Learning (RL), and cross-domain training strategies utilizing relational database (SQL) data to the Text-to-Cypher task.