Cut Costs, Not Accuracy: LLM-Powered Data Processing with Guarantees
Summary: Targets LLM cascade cost-quality tradeoffs by provable selection of when to use cheaper LLMs for record processing, addressing weak quality estimation in prior confidence-based cascades. BARGAIN uses adaptive sampling and statistical estimation tuned to data/task to give tight theoretical guarantees (accuracy/precision/recall) and empirically reduces cost up to 86% vs. state-of-the-art. (summarized by gpt-5-mini on Feb 11 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Sepanta Zeighami (University of California Berkeley)
- 2. Shreya Shankar (University of California Berkeley)
- 3. Aditya Parameswaran (University of California Berkeley)
BibTeX Citation
@inproceedings{zeighami_sigmod26,
title = {{Cut Costs, Not Accuracy: LLM-Powered Data Processing with Guarantees}},
author = {Zeighami, Sepanta and Shankar, Shreya and Parameswaran, Aditya},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3769776},
url = {https://dl.acm.org/doi/10.1145/3769776},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 2 of 2 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,199 | Automated Discovery of Test Oracles for Database Management Systems Using LLMs | 2026 | SIGMOD | 5.093636e-05 |
| 10,286 | ScaleDoc: Scaling LLM-based Predicates over Large Document Collections | 2026 | SIGMOD | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 22 of 22 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 | 13,343 | Database Perspective on LLM Inference Systems | 2025 | VLDB |
| 2 | 713 | Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes | 2024 | VLDB |
| 3 | 4,050 | Revisiting Prompt Engineering via Declarative Crowdsourcing | 2024 | CIDR |
| 4 | 10,614 | LLM-AutoDP: Automatic Data Processing via LLM Agents for Model Fine-tuning | 2026 | VLDB |
| 5 | 6,101 | LLM for Data Management | 2024 | VLDB |
| 6 | 10,733 | ScaleLLM: A Technique for Scalable LLM-augmented Data Systems | 2025 | SIGMOD |
| 7 | 7,316 | SpareLLM: Automatically Selecting Task-Specific Minimum-Cost Large Language Models under Equivalence Constraint | 2025 | SIGMOD |
| 8 | 10,504 | Task Cascades for Efficient Unstructured Data Processing | 2026 | SIGMOD |
| 9 | 10,856 | Optimized Batch Prompting for Cost-effective LLMs | 2025 | VLDB |
| 10 | 8,627 | ThriftLLM: On Cost-Effective Selection of Large Language Models for Classification Queries | 2025 | VLDB |