Semantic Operators and Their Optimization: Enabling LLM-Based Data Processing with Accuracy Guarantees in LOTUS
Summary: LOTUS introduces semantic operators for LLM-based filtering, joins, sorting, and aggregation with statistical accuracy guarantees via reference algorithms. Its optimizer composes model calls to cut costs—up to 1,000×—while preserving quality across real analytics workloads. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Liana Patel (Stanford University)
- 2. Siddharth Jha (University of California Berkeley)
- 3. Melissa Pan (University of California Berkeley)
- 4. Harshit Gupta (Stanford University)
- 5. Parth Asawa (University of California Berkeley)
- 6. Carlos Guestrin (Stanford University)
- 7. Matei Zaharia (University of California Berkeley)
BibTeX Citation
@article{patel_vldb25,
title = {{Semantic Operators and Their Optimization: Enabling LLM-Based Data Processing with Accuracy Guarantees in LOTUS}},
author = {Patel, Liana and Jha, Siddharth and Pan, Melissa and Gupta, Harshit and Asawa, Parth and Guestrin, Carlos and Zaharia, Matei},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {18},
number = {11},
pages = {4171--4184},
doi = {10.14778/3749646.3749685},
url = {https://doi.org/10.14778/3749646.3749685},
year = {2025}
}Incoming Citations (Sorted by Pagerank)
Showing 3 of 3 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 4,081 | Abacus: A Cost-Based Optimizer for Semantic Operator Systems | 2026 | VLDB | 6.9165634e-05 |
| 10,286 | ScaleDoc: Scaling LLM-based Predicates over Large Document Collections | 2026 | SIGMOD | 5.093636e-05 |
| 10,504 | Task Cascades for Efficient Unstructured Data Processing | 2026 | SIGMOD | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 11 of 11 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next