QUEST: Query Optimization in Unstructured Document Analysis
Summary: QUEST optimizes LLM-powered document queries with indexed, evidence-augmented extraction that limits text sent to models. Instance-specific, cost-aware plans reorder operators and turn joins into filters, yielding 30%–6× savings with higher F1. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Zhaoze Sun (Beijing Institute of Technology)
- 2. Chengliang Chai (Beijing Institute of Technology)
- 3. Qiyan Deng (Beijing Institute of Technology)
- 4. Kaisen Jin (Beijing Institute of Technology)
- 5. Xinyu Guo (University of Arizona)
- 6. Han Han (University of Arizona)
- 7. Ye Yuan (Beijing Institute of Technology)
- 8. Guoren Wang (Beijing Institute of Technology)
- 9. Lei Cao (University of Arizona)
BibTeX Citation
@article{sun_vldb25,
title = {{QUEST: Query Optimization in Unstructured Document Analysis}},
author = {Sun, Zhaoze and Chai, Chengliang and Deng, Qiyan and Jin, Kaisen and Guo, Xinyu and Han, Han and Yuan, Ye and Wang, Guoren and Cao, Lei},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {18},
number = {11},
pages = {4560--4573},
doi = {10.14778/3749646.3749713},
url = {https://doi.org/10.14778/3749646.3749713},
year = {2025}
}Incoming Citations (Sorted by Pagerank)
Showing 9 of 9 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 6,615 | Multi-Objective Agentic Rewrites for Unstructured Data Processing | 2026 | VLDB | 5.7164252e-05 |
| 8,708 | Unstructured Data Analysis Using LLMs: A Comprehensive Benchmark | 2026 | VLDB | 5.2705676e-05 |
| 9,096 | MoDora: Tree-Based Semi-Structured Document Analysis System | 2026 | SIGMOD | 5.208561e-05 |
| 10,232 | Featurized-Decomposition Join: Low-Cost Semantic Joins with Guarantees | 2026 | VLDB | 5.0432098e-05 |
| 10,418 | Evergreen: Efficient Claim Verification for Semantic Aggregates | 2027 | VLDB | 4.9605343e-05 |
| 10,484 | AgenticScholar: Agentic Data Management with Pipeline Orchestration for Scholarly Corpora | 2026 | SIGMOD | 4.9605343e-05 |
| 10,500 | Bridging the Gap: Cardinality Estimation for Semantic Queries on Unstructured Data | 2026 | SIGMOD | 4.9605343e-05 |
| 10,912 | Bolt-on, Verifiable Provenance for LLM-Powered Data Processing | 2026 | VLDB | 4.9605343e-05 |
| 11,030 | QuWARTS: Query Workload Aware Relational Table Synthesis from Unstructured Text | 2026 | VLDB | 4.9605343e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 10 of 10 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 | 11,030 | QuWARTS: Query Workload Aware Relational Table Synthesis from Unstructured Text | 2026 | VLDB |
| 2 | 10,903 | ReSequel: Robust LLM-assisted Query Rewriting and Optimization using Templatization and Sampling | 2026 | VLDB |
| 3 | 11,219 | Doctopus: A System for Budget-aware Structural Data Extraction from Unstructured Documents | 2025 | SIGMOD |
| 4 | 998 | To Search or to Crawl? Towards a Query Optimizer for Text-Centric Tasks | 2006 | SIGMOD |
| 5 | 6,584 | Can Large Language Models Be Query Optimizer for Relational Databases? | 2026 | SIGMOD |
| 6 | 10,231 | Task Cascades for Efficient Unstructured Data Processing | 2026 | SIGMOD |
| 7 | 8,708 | Unstructured Data Analysis Using LLMs: A Comprehensive Benchmark | 2026 | VLDB |
| 8 | 3,717 | Logical and Physical Optimizations for SQL Query Execution over Large Language Models | 2025 | SIGMOD |
| 9 | 1,895 | QUEST: A Keyword Search System for Relational Data based on Semantic and Machine Learning Techniques | 2013 | VLDB |
| 10 | 8,198 | DocDB: A Database for Unstructured Document Analysis | 2025 | VLDB |