Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2504.10950 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912714240032768 |
|---|---|
| author | Bodensohn, Jan-Micha Brackmann, Ulf Vogel, Liane Sanghi, Anupam Binnig, Carsten |
| author_facet | Bodensohn, Jan-Micha Brackmann, Ulf Vogel, Liane Sanghi, Anupam Binnig, Carsten |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_10950 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Unveiling Challenges for LLMs in Enterprise Data Engineering Bodensohn, Jan-Micha Brackmann, Ulf Vogel, Liane Sanghi, Anupam Binnig, Carsten Databases 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. |
| title | Unveiling Challenges for LLMs in Enterprise Data Engineering |
| topic | Databases |
| url | https://arxiv.org/abs/2504.10950 |