Systems Group at TADA @ VLDB'24

LLMs for Data Engineering on Enterprise Data

2024/08/25

Authors: Jan-Micha Bodensohn*, Ulf Brackmann* (SAP & DFKI), Liane Vogel*, Matthias Urban, Anupam Snaghi, Carsten Binnig

Our paper on LLMs for Data Engineering on Enterprise Data will be presented at TADA @ VLDB'24

In this paper we investigate the performance of Large Language Models (LLMs) on data engineering tasks using a real-world enterprise dataset, specifically focusing on the task of column type annotation. The study reveals that LLMs face significant challenges when applied to enterprise data, highlighting the need for further adaptation to improve their accuracy in this context.

The paper will be presented at the TADA Workshop on 8/30/2024 in Session 3: LLMs & Tabular Data.

The paper can be found here (opens in new tab)