NODES 2024 – LLM Query Benchmarks: Cypher vs SQL

Modern businesses have lots of diverse data for making decisions. However, the complexity of analysing this data can make it practically useless for decision-makers. How can we make querying complex data more accessible?

This talk explores the cutting-edge capabilities of large language models (LLMs) in translating user requests into Cypher and SQL. We assess such factors as dataset complexity, query intricacy, and the impact of few-shot examples on query quality. Which LLM does a better translator job?

Elena Kohlwey and Rinat Abdullin will present cases from multiple industries and introduce an LLM benchmark to pick the best language model for your needs.