Bridging the Gap: Cardinality Estimation for Semantic Queries on Unstructured Data
Summary: SemStats estimates cardinalities for LLM-driven semantic queries over unstructured data using a semantic catalog/index and lightweight learned judges. Stratified importance sampling yields up to 25× lower error and 31× lower latency than prior methods. (summarized by gpt-5.6-luna on Jul 26 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Shihui Xu (Tsinghua University)
- 2. Jiayi Wang (Tsinghua University)
- 3. Guoliang Li (Tsinghua University)
BibTeX Citation
@inproceedings{xu_sigmod26,
title = {{Bridging the Gap: Cardinality Estimation for Semantic Queries on Unstructured Data}},
author = {Xu, Shihui and Wang, Jiayi and Li, Guoliang},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3802024},
url = {https://dl.acm.org/doi/10.1145/3802024},
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 23 of 23 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 | 13,682 | SemExplorer: A User Interface for Semantic Approach to Customized Dataset Search | 2025 | SIGMOD |
| 2 | 5,457 | Sample-Efficient Cardinality Estimation Using Geometric Deep Learning | 2024 | VLDB |
| 3 | 10,480 | Accelerating Approximate Analytical Join Queries over Unstructured Data with Statistical Guarantees | 2026 | SIGMOD |
| 4 | 10,928 | Sema: A High-performance System for LLM-based Semantic Query Processing | 2026 | VLDB |
| 5 | 7,440 | Cardinality Estimation of Approximate Substring Queries using Deep Learning | 2022 | VLDB |
| 6 | 5,837 | Pre-training Summarization Models of Structured Datasets for Cardinality Estimation | 2022 | VLDB |
| 7 | 4,703 | Learned Cardinality Estimation for Similarity Queries | 2021 | SIGMOD |
| 8 | 4,996 | SemBench: A Benchmark for Semantic Query Processing Engines | 2026 | VLDB |
| 9 | 6,485 | Cardinality Estimation over Knowledge Graphs with Embeddings and Graph Neural Networks | 2024 | SIGMOD |
| 10 | 11,108 | Semantic Data Systems: From Data Management to Data Understanding | 2026 | VLDB |