Enhancing Text2Cypher with Schema Filtering

TL;DR

This paper investigates schema filtering techniques to improve Text2Cypher query generation, reducing costs and noise, especially benefiting smaller models, while analyzing the impact on performance and token efficiency.

Contribution

It introduces and evaluates various schema filtering methods for Text2Cypher, demonstrating their effectiveness in optimizing query generation and reducing computational costs.

Findings

Schema filtering reduces token length and costs.

Smaller models benefit more from schema filtering.

Larger models are less affected by schema filtering.

Abstract

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.