Can Foundation Models Wrangle Your Data?
Summary: Casts five data-cleaning and integration tasks as prompts, showing large foundation models achieve state-of-the-art performance without task-specific fine-tuning. Highlights privacy/domain adaptation challenges and accessibility opportunities for data management. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Avanika Narayan (Stanford University)
- 2. Ines Chami (Numbers Station)
- 3. Laurel Orr (Stanford University)
- 4. Christopher Ré (Stanford University)
BibTeX Citation
@article{narayan_vldb23,
title = {{Can Foundation Models Wrangle Your Data?}},
author = {Narayan, Avanika and Chami, Ines and Orr, Laurel and Ré, Christopher},
journal = {PVLDB},
series = {{VLDB} '23},
volume = {16},
number = {4},
pages = {738--746},
doi = {10.14778/3574245.3574258},
url = {https://doi.org/10.14778/3574245.3574258},
year = {2023}
}Incoming Citations (Sorted by Pagerank)
Showing 15 of 65 citing papers.
Outgoing Citations (Sorted by Pagerank)
Showing 15 of 15 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 11,584 | Unstructured Data Fusion for Schema and Data Extraction | 2024 | SIGMOD |
| 2 | 13,659 | From Big Time Series Forecasting to Foundation Models for Structured Data | 2026 | VLDB |
| 3 | 7,322 | Mind the Data Gap: Bridging LLMs to Enterprise Data Integration | 2025 | CIDR |
| 4 | 4,729 | LLM for Data Management | 2024 | VLDB |
| 5 | 3,659 | Revisiting Prompt Engineering via Declarative Crowdsourcing | 2024 | CIDR |
| 6 | 9,872 | Automating the Enterprise with Foundation Models | 2024 | VLDB |
| 7 | 13,657 | Graph Foundation Models: State of the Art and Future Directions | 2026 | VLDB |
| 8 | 1,838 | CHORUS: Foundation Models for Unified Data Discovery and Exploration | 2024 | VLDB |
| 9 | 11,875 | Data Management Opportunities for Foundation Models | 2022 | CIDR |
| 10 | 7,388 | Towards Foundation Database Models | 2025 | CIDR |