Making LLMs Work for Enterprise Data Tasks

TL;DR

This paper evaluates how well large language models perform on enterprise database tasks like text-to-SQL and column-type detection, revealing significant challenges and proposing solutions for practical enterprise use.

Contribution

It provides experimental insights into LLMs' performance on enterprise data tasks and discusses key challenges and potential solutions for deploying LLMs in enterprise workflows.

Findings

LLMs perform poorly on enterprise datasets compared to benchmark datasets.

Latency, cost, and quality are major challenges in enterprise LLM deployment.

Proposed solutions aim to improve LLM utility in enterprise data management.

Abstract

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.