DocDB: A Database for Unstructured Document Analysis
Summary: DocDB targets LLM extraction as the bottleneck in SQL-like document analytics. Its two-level relevance index and document-adaptive plans selectively process text and minimize costly, heterogeneous extraction calls. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Zequn Li (Beijing Institute of Technology)
- 2. Yuanhao Zhong (Beijing Institute of Technology)
- 3. Chengliang Chai (Beijing Institute of Technology)
- 4. Zhaoze Sun (Beijing Institute of Technology)
- 5. Yuhao Deng (Beijing Institute of Technology)
- 6. Ye Yuan (Beijing Institute of Technology)
- 7. Guoren Wang (Beijing Institute of Technology)
- 8. Lei Cao (University of Arizona)
BibTeX Citation
@article{li_vldb25,
title = {{DocDB: A Database for Unstructured Document Analysis}},
author = {Li, Zequn and Zhong, Yuanhao and Chai, Chengliang and Sun, Zhaoze and Deng, Yuhao and Yuan, Ye and Wang, Guoren and Cao, Lei},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {18},
number = {12},
pages = {5387--5390},
doi = {10.14778/3750601.3750678},
url = {https://doi.org/10.14778/3750601.3750678},
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 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 |
|---|---|---|---|---|
| 1,245 | Palimpzest: Optimizing AI-Powered Analytics with Declarative Query Processing | 2025 | CIDR | 0.00011507415 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 5,220 | Databases Unbound: Querying All of the World’s Bytes with AI | 2024 | VLDB |
| 2 | 4,886 | Chat2Data: An Interactive Data Analysis System with RAG, Vector Databases and LLMs | 2024 | VLDB |
| 3 | 10,572 | Relational Deep Dive: Error-Aware Queries Over Unstructured Data | 2026 | VLDB |
| 4 | 10,504 | Task Cascades for Efficient Unstructured Data Processing | 2026 | SIGMOD |
| 5 | 11,186 | Unstructured Data Fusion for Schema and Data Extraction | 2024 | SIGMOD |
| 6 | 10,286 | ScaleDoc: Scaling LLM-based Predicates over Large Document Collections | 2026 | SIGMOD |
| 7 | 1,343 | DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing | 2025 | VLDB |
| 8 | 6,371 | QUEST: Query Optimization in Unstructured Document Analysis | 2025 | VLDB |
| 9 | 8,340 | Doctopus: Budget-aware Structural Table Extraction from Unstructured Documents | 2025 | VLDB |
| 10 | 10,719 | Doctopus: A System for Budget-aware Structural Data Extraction from Unstructured Documents | 2025 | SIGMOD |