Enhancing Text2Cypher with Schema Filtering
This work addresses efficiency and cost issues in natural language to Cypher query translation for knowledge graph applications, but it is incremental as it builds on existing schema-based approaches.
The paper tackles the problem of noise and computational costs in Text2Cypher systems by exploring schema filtering methods to include only relevant database schema elements, resulting in improved query generation and reduced token costs, especially for smaller models.
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.