QueryArtisan: Generating Data Manipulation Codes for Ad-hoc Analysis in Data Lakes
Summary: LLM-driven QueryArtisan generates just-in-time data-manipulation code to enable natural-language ad-hoc queries directly over heterogeneous, schema-less data lakes using modality-aware operators. Integrates a cost-model optimizer to produce efficient operator plans, avoiding ETL/schemas and outperforming prior LLM and ETL approaches. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Xiu Tang (Hangzhou High-Tech Zone (Binjiang) Blockchain and Data Security Research Institute; Zhejiang University)
- 2. Wenhao Liu (Hangzhou High-Tech Zone (Binjiang) Blockchain and Data Security Research Institute; Zhejiang University)
- 3. Sai Wu (Hangzhou High-Tech Zone (Binjiang) Blockchain and Data Security Research Institute; Zhejiang University)
- 4. Chang Yao (Hangzhou High-Tech Zone (Binjiang) Blockchain and Data Security Research Institute; Zhejiang University)
- 5. Gongsheng Yuan (Hangzhou High-Tech Zone (Binjiang) Blockchain and Data Security Research Institute; Zhejiang University)
- 6. Shanshan Ying (ApeCloud)
- 7. Gang Chen (Hangzhou High-Tech Zone (Binjiang) Blockchain and Data Security Research Institute; Zhejiang University)
BibTeX Citation
@article{tang_vldb25,
title = {{QueryArtisan: Generating Data Manipulation Codes for Ad-hoc Analysis in Data Lakes}},
author = {Tang, Xiu and Liu, Wenhao and Wu, Sai and Yao, Chang and Yuan, Gongsheng and Ying, Shanshan and Chen, Gang},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {18},
number = {2},
pages = {108--116},
doi = {10.14778/3705829.3705832},
url = {https://doi.org/10.14778/3705829.3705832},
year = {2025}
}Incoming Citations (Sorted by Pagerank)
Showing 2 of 2 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,506 | This is Going to Sound Crazy, But What If We Used Large Language Models to Boost Automatic Database Tuning Algorithms By Leveraging Prior History? We Will Find Better Configurations More Quickly Than Retraining From Scratch! | 2026 | SIGMOD | 5.093636e-05 |
| 11,025 | A Demonstration of QueryArtisan: Real-Time Data Lake Analysis via Dynamically Generated Data Manipulation Code | 2025 | VLDB | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 17 of 17 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 | 10,139 | Leveraging Query Optimizers to Verify the Soundness of LLM-based Query Rewrites for Real-World Workloads, and More! | 2026 | CIDR |
| 2 | 6,101 | LLM for Data Management | 2024 | VLDB |
| 3 | 11,120 | Welding Natural Language Queries to Analytics IRs with LLMs | 2024 | CIDR |
| 4 | 8,906 | Unveiling Challenges for LLMs in Enterprise Data Engineering | 2026 | VLDB |
| 5 | 8,903 | DataLoom: Simplifying Data Loading with LLMs | 2024 | VLDB |
| 6 | 4,045 | Logical and Physical Optimizations for SQL Query Execution over Large Language Models | 2025 | SIGMOD |
| 7 | 7,809 | Can Large Language Models Be Query Optimizer for Relational Databases? | 2026 | SIGMOD |
| 8 | 7,439 | AOP: Automated and Interactive LLM Pipeline Orchestration for Answering Complex Queries | 2025 | CIDR |
| 9 | 713 | Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes | 2024 | VLDB |
| 10 | 11,025 | A Demonstration of QueryArtisan: Real-Time Data Lake Analysis via Dynamically Generated Data Manipulation Code | 2025 | VLDB |