DataLoom: Simplifying Data Loading with LLMs
Summary: DataLoom maps chaotic file collections to initial schemas using LLMs for semantic tasks (header inference, column typing, table merging). It orchestrates LLMs for soft decisions and classical algorithms for hard constraints to minimize manual effort and time-to-first-insight. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Alexander van Renen (University of Technology Nuremberg)
- 2. Mihail Stoian (University of Technology Nuremberg)
- 3. Andreas Kipf (University of Technology Nuremberg)
BibTeX Citation
@article{renen_vldb24,
title = {{DataLoom: Simplifying Data Loading with LLMs}},
author = {van Renen, Alexander and Stoian, Mihail and Kipf, Andreas},
journal = {PVLDB},
series = {{VLDB} '24},
volume = {17},
number = {12},
pages = {4449--4452},
doi = {10.14778/3685800.3685897},
url = {https://doi.org/10.14778/3685800.3685897},
year = {2024}
}Incoming Citations (Sorted by Pagerank)
Showing 2 of 2 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 3,900 | SQLStorm: Taking Database Benchmarking into the LLM Era | 2025 | VLDB | 6.9320915e-05 |
| 11,429 | Large Language Models for Spatial Analysis Queries | 2025 | VLDB | 4.9769913e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 7 of 7 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 52 | The Snowflake Elastic Data Warehouse | 2016 | SIGMOD | 0.00041210636 |
| 71 | DuckDB: an Embeddable Analytical Database | 2019 | SIGMOD | 0.00037724477 |
| 624 | Data Lake Management: Challenges and Opportunities | 2019 | VLDB | 0.00015476813 |
| 694 | JOSIE: Overlap Set Similarity Search for Finding Joinable Tables in Data Lakes | 2019 | SIGMOD | 0.00014721161 |
| 972 | The Data Civilizer System | 2017 | CIDR | 0.00012757732 |
| 1,394 | Data Profiling with Metanome | 2015 | VLDB | 0.00010791559 |
| 5,362 | Can Large Language Models Predict Data Correlations from Column Names? | 2023 | VLDB | 6.1592249e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 11,292 | CatDB: Data-catalog-guided, LLM-based Generation of Data-centric ML Pipelines | 2025 | VLDB |
| 2 | 3,236 | How Large Language Models Will Disrupt Data Management | 2023 | VLDB |
| 3 | 496 | Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes | 2024 | VLDB |
| 4 | 10,344 | QueryArtisan: Generating Data Manipulation Codes for Ad-hoc Analysis in Data Lakes | 2025 | VLDB |
| 5 | 11,396 | A Demonstration of QueryArtisan: Real-Time Data Lake Analysis via Dynamically Generated Data Manipulation Code | 2025 | VLDB |
| 6 | 11,047 | Semantic Data Systems: From Data Management to Data Understanding | 2026 | VLDB |
| 7 | 13,631 | Demonstrating CatDB: LLM-based Generation of Data-centric ML Pipelines | 2025 | SIGMOD |
| 8 | 9,078 | Unveiling Challenges for LLMs in Enterprise Data Engineering | 2026 | VLDB |
| 9 | 11,170 | ScaleLLM: A Technique for Scalable LLM-augmented Data Systems | 2025 | SIGMOD |
| 10 | 4,727 | LLM for Data Management | 2024 | VLDB |