Text-to-Cypher

Follow this topic Ask about this topic

Text-to-Cypher studies how to turn natural-language questions into executable Cypher queries over graph databases, so people can retrieve and reason over structured data without writing queries themselves. Common approaches ground generation in graph schemas and examples, fine-tune models on validated or synthetic query pairs, and use database execution feedback, retries, and structural checks to catch errors. Systems are evaluated on query execution accuracy across graph schemas and increasingly on enterprise, noisy, dynamic, and multi-turn settings. Queries can often be made more executable, but reliable semantic correctness, coverage, and session-level performance remain difficult, especially when graphs or user intent change.

Latest papers

12 papers1 paper in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

CypherTurn: A Multi-Turn Benchmark for Conversational Text-to-Cypher Evaluation and the Autonomy Divergence
Sep 29, 2026Yuzhe Zhang, Weijie Zhu, Haolin Yang +5LLM Evaluation Text-to-Cypher
Peking University · National Key Lab of Data Space Technology and System · Baidu Inc.
What Drives Recovery in Agentic Text-to-Cypher? LAST-CQ: An LLM Agent Self-Refinement Framework
Sep 11, 2026Ioannis Prokopiou, Athanasios Aidinis, Panagiotis-Christos Kyrmpatsos +1LLM Self-Refinement LLM Agent Evaluation
Athens University of Economics and Business · Orfium
Decoupling Error Attribution in Cloud-Native Graph-RAG: A Data Integrity Diagnostic Framework
Sep 10, 2026Shuai Yan, Yuhang Wu, Xiaodong Huang +1Graph Retrieval-Augmented Generation Retrieval-Augmented Generation
College of Computer and Software Chengdu Jincheng College Chengdu 611731, China
KG2Cypher: Data-Centric Pipeline for Building Enterprise Text-to-Cypher Systems
Jun 26, 2026Minjun Choi, Yerin Kim, Junghyuk Seo +3Text-to-Cypher Knowledge Graph Question Answering
Sungkyunkwan University · NAVER
Achieving Precise Text-To-Cypher Via Grounded Knowledge Graph Data Generation
Jun 12, 2026Francesco Cazzaro, Jessica Lennon, Ariadna QuattoniText-to-Cypher Synthetic Data Generation for Language Models
Universitat Politècnica de Catalunya, Barcelona, Spain
PIPE-Cypher: Automatic Enterprise Benchmark Generation for Text-to-Cypher Systems
Jun 7, 2026Suraj Ranganath, Anish RaghavendraBenchmark Design Text-to-Cypher
Halıcıoğlu School of Data Science and Computing University of California, San Diego · Independent Researcher
CYGNET: Cypher Gate for Neural Execution Triage and Cost Containment
Jun 3, 2026Nikodem TomczakText-to-Cypher Knowledge Graph Question Answering
Thulge Labs, Singapore
Knowledge Graphs as the Missing Data Layer for LLM-Based Industrial Asset Operations
May 26, 2026Madhulatha Mandarapu, Sandeep KunkunuruLLM Grounding Text-to-Cypher
VaidhyaMegha Private Limited, India
RAS: Reflection-Augmented Scaling with In-Context Learning for Executable Cypher Query Generation
May 21, 2026Minseok Jung, Abhas Ricky, Muhammad Rameez ChatniExecution-Guided Code Generation Inference-Time Scaling
Cloudera 6220 America Center Dr. San Jose, CA 95002
Extending Confidence-Based Text2Cypher with Grammar and Schema Aware Filtering
May 11, 2026Makbule Gulcin OzsoyLLM Inference Text-to-Cypher
Neo4j, London, UK
Graphs RAG at Scale: Beyond Retrieval-Augmented Generation With Labeled Property Graphs and Resource Description Framework for Complex and Unknown Search Spaces
Mar 21, 2026Manie Tadayon, Mayank GuptaGraph Retrieval-Augmented Generation Graph-Based Retrieval
AI Scientist, Capital Group
NGDBench: Towards Neural Graph Data Management
Feb 27, 2026Yufei Li, Yisen Gao, Jiaxuan Xiong +6Graph Retrieval-Augmented Generation Text-to-Cypher
HKUST · Beijing Institute of Technology · Hong Kong Baptist University +1

Sep 29, 2026J/K move · Enter open · S save

CypherTurn: A Multi-Turn Benchmark for Conversational Text-to-Cypher Evaluation and the Autonomy Divergence

Yuzhe Zhang, Weijie Zhu, Haolin Yang, Ziyun Zhang+4

Peking University · National Key Lab of Data Space Technology and System · Baidu Inc.

LLM Evaluation Text-to-Cypher AI Agent Benchmarks Multi-Turn Dialogue Evaluation

Open paper AskPDF arXiv

Graph databases are increasingly queried through natural language, yet every existing benchmark evaluates isolated single-turn queries rather than the multi-turn sessions through which analysts actually work. We introduce CypherTurn, the first benchmark for conversational Text-to-Cypher evaluation, comprising 721 sessions and 5,927 turns across 7 knowledge graphs and 13 conversational phenomena. We evaluate 15 models under a guided oracle protocol and a fully autonomous agentic protocol, yielding four findings. First, the best model reaches only 64.7% execution accuracy, and session-level correctness remains below 5%. Second, despite strong overall rank correlation, frontier models exhibit a consequential reordering of the top of the leaderboard under autonomous operation, a phenomenon we term the Autonomy Divergence, which reveals error-management as a partially independent capability from raw generation skill. Third, scaling action budgets from x3 to x10 fails to close the autonomy gap, as the strongest frontier models self-limit to approximately two actions per turn regardless of available budget. Fourth, single-turn Cypher fine-tuning degrades multi-turn instruction following, while architecture-appropriate specialization outperforms several frontier models. These results establish CypherTurn as an open challenge for conversational graph database reasoning. Code and data are available at https://github.com/BarryQ/CypherTurn.