Chorus: Foundation Models for Unified Data Discovery and Exploration
Proceedings of the VLDB Endowment · 2024-04 · 17 (8) · 2104-2114
DOI: 10.14778/3659437.3659461 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the VLDB Endowment, online erschienen am 31.05.2024. Verfasst von Moe Kayali und 5 weiteren Autor:innen. Die Arbeit wurde bisher 39-mal zitiert (Crossref) und nennt 67 Literaturangaben.
Abstract (Originalsprache)
We apply foundation models to data discovery and exploration tasks. Foundation models are large language models (LLMS) that show promising performance on a range of diverse tasks unrelated to their training. We show that these models are highly applicable to the data discovery and data exploration domain. When carefully used, they have superior capability on three representative tasks: table-class detection, column-type annotation and join-column prediction. On all three tasks, we show that a foundation-model-based approach outperforms the task-specific models and so the state of the art. Further, our approach often surpasses human-expert task performance. We investigate the fundamental characteristics of this approach including generalizability to several foundation models and the impact of non-determinism on the outputs. All in all, this suggests a future direction in which disparate data management tasks can be unified under foundation models.
Zitieren
APA
Kayali, M., Lykov, A., Fountalis, I., Vasiloglou, N., Olteanu, D., & Suciu, D. (2024). Chorus: Foundation Models for Unified Data Discovery and Exploration. Proceedings of the VLDB Endowment, 17(8), 2104-2114. https://doi.org/10.14778/3659437.3659461
Vancouver
Kayali M, Lykov A, Fountalis I, Vasiloglou N, Olteanu D, Suciu D. Chorus: Foundation Models for Unified Data Discovery and Exploration. Proceedings of the VLDB Endowment. 2024;17(8):2104-2114. doi:10.14778/3659437.3659461
BibTeX
@article{Kayali2024,
author = {Kayali, Moe and Lykov, Anton and Fountalis, Ilias and Vasiloglou, Nikolaos and Olteanu, Dan and Suciu, Dan},
title = {Chorus: Foundation Models for Unified Data Discovery and Exploration},
journal = {Proceedings of the VLDB Endowment},
year = {2024},
volume = {17},
number = {8},
pages = {2104--2114},
doi = {10.14778/3659437.3659461}
}
EUVIMED