ScaleLLM: A Technique for Scalable LLM-augmented Data Systems
Summary: ScaleLLM labels a small subset with a lightweight model for large-scale inference, cutting latency and cost. Achieves 37× speed with ~1% accuracy loss, enabling cost-accuracy trade-offs and reusable embedding views for LLM-augmented query optimization. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Ashwin Alaparthi (University of Pennsylvania)
- 2. Paul Loh (University of Pennsylvania)
- 3. Ryan Marcus (University of Pennsylvania)
BibTeX Citation
@inproceedings{alaparthi_sigmod25,
title = {{ScaleLLM: A Technique for Scalable LLM-augmented Data Systems}},
author = {Alaparthi, Ashwin and Loh, Paul and Marcus, Ryan},
series = {{SIGMOD} '25},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3722212.3725130},
url = {https://dl.acm.org/doi/10.1145/3722212.3725130},
year = {2025}
}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 2 of 2 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 92 | CrowdDB: Answering Queries with Crowdsourcing | 2011 | SIGMOD | 0.00034672523 |
| 4,787 | Hybrid Querying Over Relational Databases and Large Language Models | 2025 | CIDR | 6.4143303e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 174 | Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation | 2024 | VLDB |
| 2 | 3,743 | Logical and Physical Optimizations for SQL Query Execution over Large Language Models | 2025 | SIGMOD |
| 3 | 8,986 | DataLoom: Simplifying Data Loading with LLMs | 2024 | VLDB |
| 4 | 9,069 | Unveiling Challenges for LLMs in Enterprise Data Engineering | 2026 | VLDB |
| 5 | 10,766 | A Comparative Evaluation of Schema Subsetting for LLM-based NL-to-SQL over Large-Schema Databases | 2026 | VLDB |
| 6 | 8,997 | Cut Costs, Not Accuracy: LLM-Powered Data Processing with Guarantees | 2026 | SIGMOD |
| 7 | 5,149 | LLM for Data Management | 2024 | VLDB |
| 8 | 13,689 | Reimagining Deep Learning Systems Through the Lens of Data Systems | 2024 | VLDB |
| 9 | 9,158 | Database Perspective on LLM Inference Systems | 2025 | VLDB |
| 10 | 10,498 | ScaleDoc: Scaling LLM-based Predicates over Large Document Collections | 2026 | SIGMOD |