mlsanityData to 14 Oct 2026

Enhancing Text2Cypher with Schema Filtering

arXiv 2505.05118 ↗First posted 8 May 2025cs.DB cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Knowledge graphs represent complex data using nodes, relationships, and properties. Cypher, a powerful query language for graph databases, enables efficient modeling and querying. Recent advancements in large language models allow translation of natural language questions into Cypher queries - Text2Cypher. A common approach is incorporating database schema into prompts. However, complex schemas can introduce noise, increase hallucinations, and raise computational costs. Schema filtering addresses these challenges by including only relevant schema elements, improving query generation while reducing token costs. This work explores various schema filtering methods for Text2Cypher task and analyzes their impact on token length, performance, and cost. Results show that schema filtering effectively optimizes Text2Cypher, especially for smaller models. Consistent with prior research, we find that larger models benefit less from schema filtering due to their longer context capabilities. However, schema filtering remains valuable for both larger and smaller models in cost reduction.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 28 of its 36 references that are in the map. First posted on arXiv 8 May 2025.

Builds on

28 of 36 references.

References · 28

  1. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,139
  2. 2020Knowledge Graphscited by 621
  3. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 477
  4. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 424
  5. 2019Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representationcited by 210
  6. 2023GPT4Graph: Can Large Language Models Understand Graph Structured Data ? An Empirical Evaluation and Benchmarkingcited by 210
  7. 2023RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQLcited by 195
  8. 2024CHESS: Contextual Harnessing for Efficient SQL Synthesiscited by 169
  9. 2018TypeSQL: Knowledge-based Type-Aware Neural Text-to-SQL Generationcited by 81
  10. 2024The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Modelscited by 67
  11. 2024RSL-SQL: Robust Schema Linking in Text-to-SQL Generationcited by 52
  12. 2019Global Reasoning over Database Structures for Text-to-SQL Parsingcited by 43
16 more
  1. 2024E-SQL: Direct Schema Linking via Question Enrichment in Text-to-SQLcited by 35
  2. 2024Text2Cypher: Bridging Natural Language and Graph Databasescited by 30
  3. 2025Is Long Context All You Need? Leveraging LLM's Extended Context for NL2SQLcited by 30
  4. 2024LLM-based SPARQL Query Generation from Natural Language over Federated Knowledge Graphscited by 22
  5. 2024SyntheT2C: Generating Synthetic Data for Fine-Tuning Large Language Models on the Text2Cypher Taskcited by 19
  6. 2024Metasql: A Generate-then-Rank Framework for Natural Language to SQL Translationcited by 17
  7. 2024Aligning Large Language Models to a Domain-specific Graph Database for NL2GQLcited by 14
  8. 2024Assessing SPARQL capabilities of Large Language Modelscited by 14
  9. 2024Leveraging small language models for Text2SPARQL tasks to improve the resilience of AI assistancecited by 13
  10. 2025Extractive Schema Linking for Text-to-SQLcited by 13
  11. 2024NAT-NL2GQL: A Novel Multi-Agent Framework for Translating Natural Language to Graph Query Languagecited by 9
  12. 2025Knapsack Optimization-based Schema Linking for LLM-based Text-to-SQL Generationcited by 9
  13. 2023S2CTrans: Building a bridge from SPARQL to Cyphercited by 6
  14. 2023Rel2Graph: Automated Mapping From Relational Databases to a Unified Property Knowledge Graphcited by 5
  15. 2024SelECT-SQL: Self-correcting ensemble Chain-of-Thought for Text-to-SQLcited by 4
  16. 2025SAFE-SQL: Self-Augmented In-Context Learning with Fine-grained Example Selection for Text-to-SQLcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 5.

6 papers.

  1. 2025STRuCT-LLM: Unifying Tabular and Graph Reasoning with Reinforcement Learning for Semantic Parsingcited by 5
  2. 2026Grounding Large Language Models in Reaction Knowledge Graphs for Synthesis Retrievalcited by 1
  3. 2026Extending Confidence-Based Text2Cypher with Grammar and Schema Aware Filteringcited by 1
  4. 2026CYGNET: Cypher Gate for Neural Execution Triage and Cost Containmentcited by 1
  5. 2026LLM+Graph@VLDB'2025 Workshop Summarycited by 0
  6. 2026What Drives Recovery in Agentic Text-to-Cypher? LAST-CQ: An LLM Agent Self-Refinement Frameworkcited by 0