Relational Deep Dive: Error-Aware Queries Over Unstructured Data
Summary: ReDD dynamically discovers query-specific, joinable schemas and populates relational tables from unstructured corpora using LLMs plus hidden-state classifiers. SCAPE provides calibrated error detection with coverage guarantees, enabling accuracy–human-cost trade-offs and reducing extraction errors below 1%. (summarized by gpt-5.6-luna on Jul 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Daren Chao (University of Toronto)
- 2. Kaiwen Chen (University of Toronto)
- 3. Naiqing Guan (University of Toronto)
- 4. Nick Koudas (University of Toronto)
BibTeX Citation
@article{chao_vldb26,
title = {{Relational Deep Dive: Error-Aware Queries Over Unstructured Data}},
author = {Chao, Daren and Chen, Kaiwen and Guan, Naiqing and Koudas, Nick},
journal = {PVLDB},
series = {{VLDB} '26},
volume = {19},
number = {8},
pages = {1840--1853},
doi = {10.14778/3811243.3811256},
url = {https://doi.org/10.14778/3811243.3811256},
year = {2026}
}
Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,960 | QuWARTS: Query Workload Aware Relational Table Synthesis from Unstructured Text | 2026 | VLDB | 4.9793485e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 12 of 12 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 | 11,024 | Bridging LLMs and Database Systems: A Deep Dive into Enhanced Relational Operators | 2026 | VLDB |
| 2 | 4,393 | Extracting Databases from Dark Data with DeepDive | 2016 | SIGMOD |
| 3 | 10,832 | ReSequel: Robust LLM-assisted Query Rewriting and Optimization using Templatization and Sampling | 2026 | VLDB |
| 4 | 8,680 | Unstructured Data Analysis Using LLMs: A Comprehensive Benchmark | 2026 | VLDB |
| 5 | 10,594 | Reliable Answers for Recurring Questions: Boosting Text-to-SQL Accuracy with Template Constrained Decoding | 2026 | SIGMOD |
| 6 | 10,632 | DIVER: A Robust Text-to-SQL System with Dynamic Interactive Value Linking and Evidence Reasoning | 2026 | SIGMOD |
| 7 | 4,557 | Databases Unbound: Querying All of the World’s Bytes with AI | 2024 | VLDB |
| 8 | 10,804 | Document-to-Database: Extraction Meets Relational Semantics | 2026 | VLDB |
| 9 | 7,012 | Reliable Text-to-SQL with Adaptive Abstention | 2025 | SIGMOD |
| 10 | 11,529 | Unstructured Data Fusion for Schema and Data Extraction | 2024 | SIGMOD |