DataMosaic: An Interactive Demonstration of Constraint-Driven Document-to-Database Construction
Summary: DataMosaic interactively constructs relational tables from documents under user-specified schemas, keys, and integrity constraints. Its closed loop of LLM extraction, constraint verification, repair, and targeted re-extraction exposes auditable snapshots and violations for reliable database materialization. (summarized by gpt-5.6-luna on Aug 28 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Zhengxuan Zhang (Hong Kong University of Science and Technology)
- 2. Zhuowen Liang (Hong Kong University of Science and Technology)
- 3. Haixun Wang (EvenUp)
- 4. Nan Tang (Hong Kong University of Science and Technology)
BibTeX Citation
@article{zhang_vldb26,
title = {{DataMosaic: An Interactive Demonstration of Constraint-Driven Document-to-Database Construction}},
author = {Zhang, Zhengxuan and Liang, Zhuowen and Wang, Haixun and Tang, Nan},
journal = {PVLDB},
series = {{VLDB} '26},
volume = {19},
number = {12},
pages = {4570--4573},
doi = {10.14778/3827998.3828068},
url = {https://doi.org/10.14778/3827998.3828068},
year = {2026}
}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 1 of 1 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,804 | Document-to-Database: Extraction Meets Relational Semantics | 2026 | VLDB | 4.9793485e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 11,380 | GalaxyWeaver: Autonomous Table-to-Graph Conversion and Schema Optimization with Large Language Models | 2025 | VLDB |
| 2 | 4,718 | Chat2Data: An Interactive Data Analysis System with RAG, Vector Databases and LLMs | 2024 | VLDB |
| 3 | 10,292 | Andromeda: Debugging Database Performance Issues with Retrieval-Augmented Large Language Models | 2025 | SIGMOD |
| 4 | 11,024 | Bridging LLMs and Database Systems: A Deep Dive into Enhanced Relational Operators | 2026 | VLDB |
| 5 | 8,679 | Relational Deep Dive: Error-Aware Queries Over Unstructured Data | 2026 | VLDB |
| 6 | 11,038 | Semantic Data Systems: From Data Management to Data Understanding | 2026 | VLDB |
| 7 | 11,008 | iPDB: SQL with ML and LLM Predicates (Towards a Database Engine for AI) | 2026 | VLDB |
| 8 | 8,632 | DocDB: A Database for Unstructured Document Analysis | 2025 | VLDB |
| 9 | 7,885 | Semantic Integrity Constraints: Declarative Guardrails for AI-Augmented Data Processing Systems | 2025 | VLDB |
| 10 | 10,804 | Document-to-Database: Extraction Meets Relational Semantics | 2026 | VLDB |