Doctopus: Budget-aware Structural Table Extraction from Unstructured Documents
Summary: Doctopus extracts structural attributes from unstructured documents under user-specified LLM budgets. It combines index-based chunk pruning, per-attribute quality estimation, and dynamic strategy selection across LLM/non-LLM methods, improving quality 11% at equal cost. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Chengliang Chai (Beijing Institute of Technology)
- 2. Jiajun Li (Beijing Institute of Technology)
- 3. Yuhao Deng (Beijing Institute of Technology)
- 4. Yuanhao Zhong (Beijing Institute of Technology)
- 5. Ye Yuan (Beijing Institute of Technology)
- 6. Guoren Wang (Beijing Institute of Technology)
- 7. Lei Cao (University of Arizona)
BibTeX Citation
@article{chai_vldb25,
title = {{Doctopus: Budget-aware Structural Table Extraction from Unstructured Documents}},
author = {Chai, Chengliang and Li, Jiajun and Deng, Yuhao and Zhong, Yuanhao and Yuan, Ye and Wang, Guoren and Cao, Lei},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {18},
number = {11},
pages = {3695--3707},
doi = {10.14778/3749646.3749647},
url = {https://doi.org/10.14778/3749646.3749647},
year = {2025}
}Incoming Citations (Sorted by Pagerank)
Showing 2 of 2 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,190 | AgenticScholar: Agentic Data Management with Pipeline Orchestration for Scholarly Corpora | 2026 | SIGMOD | 5.093636e-05 |
| 10,433 | Beyond Relational: Semantic-Aware Multi-Modal Analytics with LLM-Native Query Optimization | 2026 | SIGMOD | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 5 of 5 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 141 | Deep Entity Matching with Pre-Trained Language Models | 2021 | VLDB | 0.0002964847 |
| 713 | Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes | 2024 | VLDB | 0.00014672521 |
| 1,550 | Symphony: Towards Natural Language Query Answering over Multi-modal Data Lakes | 2023 | CIDR | 0.00010385904 |
| 2,175 | From Natural Language Processing to Neural Databases | 2021 | VLDB | 9.0215773e-05 |
| 3,684 | ThalamusDB: Approximate Query Processing on Multi-Modal Data | 2024 | SIGMOD | 7.2033959e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 1,923 | Annotating Columns with Pre-trained Language Models | 2022 | SIGMOD |
| 2 | 9,972 | Cents: A Flexible and Cost-Effective Framework for LLM-Based Table Understanding | 2025 | VLDB |
| 3 | 10,270 | MoDora: Tree-Based Semi-Structured Document Analysis System | 2026 | SIGMOD |
| 4 | 10,286 | ScaleDoc: Scaling LLM-based Predicates over Large Document Collections | 2026 | SIGMOD |
| 5 | 11,980 | Building Structured Databases of Factual Knowledge from Massive Text Corpora | 2017 | SIGMOD |
| 6 | 6,371 | QUEST: Query Optimization in Unstructured Document Analysis | 2025 | VLDB |
| 7 | 11,186 | Unstructured Data Fusion for Schema and Data Extraction | 2024 | SIGMOD |
| 8 | 1,343 | DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing | 2025 | VLDB |
| 9 | 13,339 | DocDB: A Database for Unstructured Document Analysis | 2025 | VLDB |
| 10 | 10,719 | Doctopus: A System for Budget-aware Structural Data Extraction from Unstructured Documents | 2025 | SIGMOD |