Making LLMs Work for Enterprise Data Tasks
This addresses the challenge of adapting LLMs for enterprise data management and analysis tasks, which is incremental as it builds on existing LLM capabilities by highlighting performance gaps and suggesting improvements.
The study tackled the problem of LLMs' poor performance on enterprise database tasks, finding that their accuracy on text-to-SQL and semantic column-type detection is significantly lower than on benchmark datasets, with specific numbers not provided. It identified latency, cost, and quality as key challenges and proposed solutions for integrating LLMs into enterprise workflows.
Large language models (LLMs) know little about enterprise database tables in the private data ecosystem, which substantially differ from web text in structure and content. As LLMs' performance is tied to their training data, a crucial question is how useful they can be in improving enterprise database management and analysis tasks. To address this, we contribute experimental results on LLMs' performance for text-to-SQL and semantic column-type detection tasks on enterprise datasets. The performance of LLMs on enterprise data is significantly lower than on benchmark datasets commonly used. Informed by our findings and feedback from industry practitioners, we identify three fundamental challenges -- latency, cost, and quality -- and propose potential solutions to use LLMs in enterprise data workflows effectively.