Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes
Summary: Evaporate uses LLM in-context learning to turn heterogeneous documents into queryable structured views, comparing direct extraction with code synthesis. Code+ ensembles weakly supervised candidate extractors, surpassing prior systems while reducing LLM document processing by 110×. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Simran Arora (Stanford University)
- 2. Brandon Yang (Stanford University)
- 3. Sabri Eyuboglu (Stanford University)
- 4. Avanika Narayan (Stanford University)
- 5. Andrew Hojel (Stanford University)
- 6. Immanuel Trummer (Cornell University)
- 7. Christopher Ré (Stanford University)
BibTeX Citation
@article{arora_vldb24,
title = {{Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes}},
author = {Arora, Simran and Yang, Brandon and Eyuboglu, Sabri and Narayan, Avanika and Hojel, Andrew and Trummer, Immanuel and Ré, Christopher},
journal = {PVLDB},
series = {{VLDB} '24},
volume = {17},
number = {2},
pages = {92--105},
doi = {10.14778/3626292.3626294},
url = {https://doi.org/10.14778/3626292.3626294},
year = {2024}
}Incoming Citations (Sorted by Pagerank)
Showing 40 of 40 citing papers.
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 11 of 11 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 | 8,897 | Optimized Batch Prompting for Cost-effective LLMs | 2025 | VLDB |
| 2 | 11,047 | Semantic Data Systems: From Data Management to Data Understanding | 2026 | VLDB |
| 3 | 9,167 | Database Perspective on LLM Inference Systems | 2025 | VLDB |
| 4 | 9,078 | Unveiling Challenges for LLMs in Enterprise Data Engineering | 2026 | VLDB |
| 5 | 4,133 | AOP: Automated and Interactive LLM Pipeline Orchestration for Answering Complex Queries | 2025 | CIDR |
| 6 | 3,236 | How Large Language Models Will Disrupt Data Management | 2023 | VLDB |
| 7 | 10,847 | EcoTable: Cost-effective Table Integration in Data Lakes for Natural Language Queries | 2026 | VLDB |
| 8 | 11,396 | A Demonstration of QueryArtisan: Real-Time Data Lake Analysis via Dynamically Generated Data Manipulation Code | 2025 | VLDB |
| 9 | 10,344 | QueryArtisan: Generating Data Manipulation Codes for Ad-hoc Analysis in Data Lakes | 2025 | VLDB |
| 10 | 4,727 | LLM for Data Management | 2024 | VLDB |