MétaCan
Menu
Back to cohort
Record W4414004064 · doi:10.14778/3749646.3749702

ThriftLLM: On Cost-Effective Selection of Large Language Models for Classification Queries

2025· article· en· W4414004064 on OpenAlexaff
Keke Huang, Yimin Shi, Dujian Ding, Yifei Li, Fei Yang, Laks V. S. Lakshmanan, Xiaokui Xiao

Bibliographic record

VenueProceedings of the VLDB Endowment · 2025
Typearticle
Languageen
FieldDecision Sciences
TopicData Quality and Management
Canadian institutionsUniversity of British Columbia
Fundersnot available
KeywordsSelection (genetic algorithm)Computer scienceNatural language processingArtificial intelligenceInformation retrieval

Abstract

fetched live from OpenAlex

Recently, large language models (LLMs) have demonstrated remarkable capabilities in understanding and generating natural language content, attracting widespread attention in both industry and academia. An increasing number of services offer LLMs for various tasks via APIs. Different LLMs demonstrate expertise in different domains of queries (e.g., text classification queries). Meanwhile, LLMs of different scales, complexities, and performance are priced diversely. Driven by this, several researchers are investigating strategies for selecting an ensemble of LLMs, aiming to decrease overall usage costs while enhancing performance. However, to our best knowledge, none of the existing works addresses the problem, how to find an LLM ensemble subject to a cost budget, which maximizes the ensemble performance with guarantees. In this paper, we formalize the performance of an ensemble of models (LLMs) using the notion of correctness probability, which we formally define. We develop an approach for aggregating responses from multiple LLMs to enhance ensemble performance. Building on this, we formulate the Optimal Ensemble Selection (OES) problem of selecting a set of LLMs subject to a cost budget that maximizes the overall correctness probability. We show that the correctness probability function is non-decreasing and non-submodular and provide evidence that the OES problem is likely to be NP-hard. By leveraging a submodular function that upper bounds correctness probability, we develop an algorithm, ThriftLLM, and prove that it achieves an instance-dependent approximation guarantee with high probability. Our framework functions as a data processing system that selects appropriate LLM operators to deliver high-quality results under budget constraints. It achieves state-of-the-art performance for text classification and entity matching queries on multiple real-world datasets against various baselines in our extensive experimental evaluation, while using a relatively lower cost budget, strongly supporting the effectiveness and superiority of our method.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.007
metaresearch head score (Gemma)0.023
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.013
Threshold uncertainty score0.035

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0070.023
Meta-epidemiology (narrow)0.0030.001
Meta-epidemiology (broad)0.0040.003
Bibliometrics0.0020.003
Science and technology studies0.0020.001
Scholarly communication0.0030.005
Open science0.0050.005
Research integrity0.0030.004
Insufficient payload (model declined to judge)0.0050.002

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.098
GPT teacher head0.415
Teacher spread0.316 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations4
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueProceedings of the VLDB EndowmentSame topicData Quality and ManagementFrench-language works237,207