Optimized Batch Prompting for Cost-effective LLMs
Summary: Formalizes batch prompting for data-management ICL as an optimization problem, analyzing its hardness and deriving efficient adaptive grouping algorithms. Evaluations on 14 datasets show lower inference cost and consistent gains over heuristic/state-of-the-art baselines. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Zhaoxuan Ji (Beijing Institute of Technology)
- 2. Xinlu Wang (Beijing Institute of Technology)
- 3. Zhaojing Luo (Beijing Institute of Technology)
- 4. Zhongle Xie (Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security; Zhejiang University)
- 5. Meihui Zhang (Beijing Institute of Technology)
BibTeX Citation
@article{ji_vldb25,
title = {{Optimized Batch Prompting for Cost-effective LLMs}},
author = {Ji, Zhaoxuan and Wang, Xinlu and Luo, Zhaojing and Xie, Zhongle and Zhang, Meihui},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {18},
number = {7},
pages = {2172--2184},
doi = {10.14778/3734839.3734853},
url = {https://doi.org/10.14778/3734839.3734853},
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 16 of 16 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 | 10,733 | ScaleLLM: A Technique for Scalable LLM-augmented Data Systems | 2025 | SIGMOD |
| 2 | 10,504 | Task Cascades for Efficient Unstructured Data Processing | 2026 | SIGMOD |
| 3 | 10,276 | OctoSelector: Efficient and Effective Batch-Aware Model Selection for Large Language Models | 2026 | SIGMOD |
| 4 | 713 | Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes | 2024 | VLDB |
| 5 | 13,343 | Database Perspective on LLM Inference Systems | 2025 | VLDB |
| 6 | 10,318 | In-context Clustering-based Entity Resolution with Large Language Models: A Design Space Exploration | 2026 | SIGMOD |
| 7 | 8,627 | ThriftLLM: On Cost-Effective Selection of Large Language Models for Classification Queries | 2025 | VLDB |
| 8 | 4,050 | Revisiting Prompt Engineering via Declarative Crowdsourcing | 2024 | CIDR |
| 9 | 8,829 | Cut Costs, Not Accuracy: LLM-Powered Data Processing with Guarantees | 2026 | SIGMOD |
| 10 | 6,101 | LLM for Data Management | 2024 | VLDB |