Mind the Data Gap: Bridging LLMs to Enterprise Data Integration

TL;DR

This paper highlights the performance gap of large language models on real-world enterprise data, introduces the GOBY Benchmark to evaluate enterprise data integration, and proposes techniques to improve LLM performance in enterprise settings.

Contribution

It introduces the GOBY Benchmark for enterprise data, and proposes novel techniques to enhance LLM performance on private enterprise datasets.

Findings

LLMs perform worse on enterprise data than public data

The GOBY Benchmark reveals the performance gap

Proposed techniques close the performance gap

Abstract

Leading large language models (LLMs) are trained on public data. However, most of the world's data is dark data that is not publicly accessible, mainly in the form of private organizational or enterprise data. We show that the performance of methods based on LLMs seriously degrades when tested on real-world enterprise datasets. Current benchmarks, based on public data, overestimate the performance of LLMs. We release a new benchmark dataset, the GOBY Benchmark, to advance discovery in enterprise data integration. Based on our experience with this enterprise benchmark, we propose techniques to uplift the performance of LLMs on enterprise data, including (1) hierarchical annotation, (2) runtime class-learning, and (3) ontology synthesis. We show that, once these techniques are deployed, the performance on enterprise data becomes on par with that of public data. The Goby benchmark can be obtained at https://goby-benchmark.github.io/.