Large Language Models (LLMs) promise to automate data engineering on tabular data, offering enterprises a valuable opportunity to cut the high costs of manual data handling. But the enterprise domain comes with unique challenges that existing LLM-based approaches for data engineering often overlook, such as large table sizes, more complex tasks, and the need for internal knowledge. To bridge these gaps, we identify key enterprise-specific challenges related to data, tasks, and background knowledge and extensively evaluate how they affect data engineering with LLMs. Our analysis reveals that LLMs face substantial limitations in real-world enterprise scenarios, with accuracy declining sharply. Our findings contribute to a systematic understanding of LLMs for enterprise data engineering to support their adoption in industry.
@article{arxiv.2504.10950,
title = {Unveiling Challenges for LLMs in Enterprise Data Engineering},
author = {Jan-Micha Bodensohn and Ulf Brackmann and Liane Vogel and Anupam Sanghi and Carsten Binnig},
journal= {arXiv preprint arXiv:2504.10950},
year = {2025}
}