Back to papers
ThriftLLM: On Cost-Effective Selection of Large Language Models for Classification Queries
Summary: Defines 'correctness probability' for LLM ensemble correctness and formulates the budgeted Optimal Ensemble Selection (OES) problem. ThriftLLM approximates the non-submodular OES via a submodular upper bound, provides instance-dependent guarantees, and yields cost-effective SOTA results.
(summarized by gpt-5-mini on Feb 09 2026)
- Paper ID
- 14055
- Venue
- VLDB
- Year
- 2025
- Pagerank
- 4.3690661e-05
- Overall Rank
- 9,235 | 35.76%
- DOI
-
10.14778/3749646.3749702
Incoming Non-self Citations Over Time
Incoming Citations (Sorted by Pagerank)
Showing 2 of 2 citing papers.
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.
| Rank |
Cited Paper |
Year |
Venue |
Pagerank |
| 180 |
Influence Maximization: Near-Optimal Time Complexity Meets Practical Efficiency |
2014 |
SIGMOD |
0.00037135181 |
| 221 |
Deep Entity Matching with Pre-Trained Language Models |
2021 |
VLDB |
0.00033121824 |
| 300 |
Deep Learning for Entity Matching: A Design Space Exploration |
2018 |
SIGMOD |
0.00028441466 |
| 369 |
Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation |
2024 |
VLDB |
0.0002547515 |
| 712 |
Magellan: Toward Building Entity Matching Management Systems |
2016 |
VLDB |
0.00017732426 |
| 754 |
Distributed Representations of Tuples for Entity Resolution |
2018 |
VLDB |
0.00017117211 |
| 814 |
Entity Resolution: Theory, Practice & Open Challenges |
2012 |
VLDB |
0.00016370594 |
| 961 |
DBSCAN Revisited: Mis-Claim, Un-Fixability, and Approximation |
2015 |
SIGMOD |
0.00015001792 |
| 1,914 |
Creating Embeddings of Heterogeneous Relational Datasets for Data Integration Tasks |
2020 |
SIGMOD |
0.00010109102 |
| 4,739 |
AutoTQA: Towards Autonomous Tabular Question Answering through Multi-Agent Large Language Models |
2024 |
VLDB |
5.959592e-05 |
| 4,837 |
Entity Resolution with Hierarchical Graph Attention Networks |
2022 |
SIGMOD |
5.8892326e-05 |
| 4,908 |
Combining Small Language Models and Large Language Models for Zero-Shot NL2SQL |
2024 |
VLDB |
5.8339245e-05 |
| 5,033 |
FinSQL: Model-Agnostic LLMs-based Text-to-SQL Framework for Financial Analysis |
2024 |
SIGMOD |
5.7486224e-05 |
| 8,052 |
Generating Succinct Descriptions of Database Schemata for Cost-Efficient Prompting of Large Language Models |
2024 |
VLDB |
4.5953106e-05 |
| 8,385 |
Are Large Language Models a Good Replacement of Taxonomies? |
2024 |
VLDB |
4.5303205e-05 |
| 9,449 |
An Interactive Multi-modal Query Answering System with Retrieval-Augmented Large Language Models |
2024 |
VLDB |
4.3399593e-05 |
Semantically Similar Papers
| Overall Rank |
Paper |
Year |
Venue |
Pagerank |
| 10,239 |
BRIEF: Bi-level Coreset Selection for Efficient Instruction Tuning in LLMs |
2026 |
VLDB |
4.1945683e-05 |
| 10,091 |
LLM-Powered Interactive Graph Search: A Scalable and Practical Approach |
2026 |
SIGMOD |
4.1945683e-05 |
| 10,215 |
Task Cascades for Efficient Unstructured Data Processing |
2026 |
SIGMOD |
4.1945683e-05 |
| 10,753 |
Cents: A Flexible and Cost-Effective Framework for LLM-Based Table Understanding |
2025 |
VLDB |
4.1945683e-05 |
| 3,840 |
Revisiting Prompt Engineering via Declarative Crowdsourcing |
2024 |
CIDR |
6.7106924e-05 |
| 10,452 |
ScaleLLM: A Technique for Scalable LLM-augmented Data Systems |
2025 |
SIGMOD |
4.1945683e-05 |
| 10,022 |
In-context Clustering-based Entity Resolution with Large Language Models: A Design Space Exploration |
2026 |
SIGMOD |
4.1945683e-05 |
| 10,595 |
Optimized Batch Prompting for Cost-effective LLMs |
2025 |
VLDB |
4.1945683e-05 |
| 7,339 |
SpareLLM: Automatically Selecting Task-Specific Minimum-Cost Large Language Models under Equivalence Constraint |
2025 |
SIGMOD |
4.7579469e-05 |
| 10,064 |
Cut Costs, Not Accuracy: LLM-Powered Data Processing with Guarantees |
2026 |
SIGMOD |
4.1945683e-05 |