EUVIMEDSkopri EUVIMED
Crossref

Unify: A System For Unstructured Data Analytics

Jiayi Wang, Yuan Li, Jianming Wu, Shihui Xu, Guoliang Li

Proceedings of the VLDB Endowment · 2025-08 · 18 (12) · 5287-5290

DOI: 10.14778/3750601.3750653 ↗

At a glance

Journal article in Proceedings of the VLDB Endowment, published online on 2025-09-16. Written by Jiayi Wang and 4 co-authors. Cited 7 times so far (Crossref); 13 references.

AstrattDettalji biblijografiċiCiteRelated studies

Abstract (original language)

Unstructured data comprises over 80% of today's information, yet no specialized system effectively supports its semantic analytics. Traditional SQL-based approaches rely on predefined schemas, making them unsuitable. While large language models (LLMs) enable semantic analysis of unstructured data, manually orchestrating execution plans remains inefficient. This raises a critical question: how can we automate unstructured data analytics? In this demonstration, we present Unify, a system that automates unstructured data analytics for natural language queries. Unify defines a set of core operators for unstructured data processing, with both preprogrammed and LLM-based implementations. It guides LLMs to decompose queries into logical steps and map them to appropriate operators for accurate execution. Our demonstration showcases Unify by real-world scenarios, highlighting its ability to bridge the gap between unstructured data and actionable analytics.

Cite

APA

Wang, J., Li, Y., Wu, J., Xu, S., & Li, G. (2025). Unify: A System For Unstructured Data Analytics. Proceedings of the VLDB Endowment, 18(12), 5287-5290. https://doi.org/10.14778/3750601.3750653

Vancouver

Wang J, Li Y, Wu J, Xu S, Li G. Unify: A System For Unstructured Data Analytics. Proceedings of the VLDB Endowment. 2025;18(12):5287-5290. doi:10.14778/3750601.3750653

BibTeX
@article{Wang2025,
  author = {Wang, Jiayi and Li, Yuan and Wu, Jianming and Xu, Shihui and Li, Guoliang},
  title = {Unify: A System For Unstructured Data Analytics},
  journal = {Proceedings of the VLDB Endowment},
  year = {2025},
  volume = {18},
  number = {12},
  pages = {5287--5290},
  doi = {10.14778/3750601.3750653}
}
Start for free →