Towards Automated Cross-domain Exploratory Data Analysis through Large Language Models
Summary: TiInsight: an end-to-end LLM-driven, cross-domain SQL EDA system that introduces hierarchical data context (HDC) to summarize schema and enable open-world generalization. Four-stage pipeline (HDC gen, question clarification/decomposition, TiSQL text-to-SQL, TiChart viz), production deployment with open APIs, achieves 86.3% exec accuracy on Spider (GPT‑4) and strong user-study gains vs experts. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Jun-Peng Zhu (East China Normal University; PingCAP)
- 2. Boyan Niu (PingCAP)
- 3. Peng Cai (East China Normal University)
- 4. Zheming Ni (PingCAP)
- 5. Jianwei Wan (PingCAP)
- 6. Kai Xu (PingCAP)
- 7. Jiajun Huang (PingCAP)
- 8. Shengbo Ma (PingCAP)
- 9. Bing Wang (PingCAP)
- 10. Xuan Zhou (East China Normal University)
- 11. Guanglei Bao (PingCAP)
- 12. Donghui Zhang (PingCAP)
- 13. Liu Tang (PingCAP)
- 14. Qi Liu (PingCAP)
BibTeX Citation
@article{zhu_vldb25,
title = {{Towards Automated Cross-domain Exploratory Data Analysis through Large Language Models}},
author = {Zhu, Jun-Peng and Niu, Boyan and Cai, Peng and Ni, Zheming and Wan, Jianwei and Xu, Kai and Huang, Jiajun and Ma, Shengbo and Wang, Bing and Zhou, Xuan and Bao, Guanglei and Zhang, Donghui and Tang, Liu and Liu, Qi},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {18},
number = {12},
pages = {5086--5099},
doi = {10.14778/3750601.3750629},
url = {https://doi.org/10.14778/3750601.3750629},
year = {2025}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 28 of 28 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 | 2,710 | OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignment | 2025 | SIGMOD |
| 2 | 10,217 | DeepEye-SQL: A Software-Engineering-Inspired Text-to-SQL Framework | 2026 | SIGMOD |
| 3 | 6,936 | Reliable Text-to-SQL with Adaptive Abstention | 2025 | SIGMOD |
| 4 | 8,906 | Unveiling Challenges for LLMs in Enterprise Data Engineering | 2026 | VLDB |
| 5 | 10,510 | NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions | 2026 | VLDB |
| 6 | 4,886 | Chat2Data: An Interactive Data Analysis System with RAG, Vector Databases and LLMs | 2024 | VLDB |
| 7 | 11,120 | Welding Natural Language Queries to Analytics IRs with LLMs | 2024 | CIDR |
| 8 | 8,140 | Automated Data Visualization from Natural Language via Large Language Models: An Exploratory Study | 2024 | SIGMOD |
| 9 | 279 | Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation | 2024 | VLDB |
| 10 | 4,308 | AutoTQA: Towards Autonomous Tabular Question Answering through Multi-Agent Large Language Models | 2024 | VLDB |