MétaCan
Menu
← Back to cohort
Record W4400488479 · doi:10.48550/arxiv.2407.06172

On Speeding Up Language Model Evaluation

2024· preprint· en· W4400488479 on OpenAlexfundno aff
Jin Zhou, Christian K. Belardi, Ruihan Wu, Travis Zhang, Carla P. Gomes, Wen Sun, Kilian Q. Weinberger

Bibliographic record

VenuearXiv (Cornell University) · 2024
Typepreprint
Languageen
FieldComputer Science
TopicNatural Language Processing Techniques
Canadian institutionsnot available
FundersArmy Research OfficeDivision of Materials ResearchOffice of Naval ResearchMultidisciplinary University Research InitiativeMaterials Research Science and Engineering Center, Harvard UniversityNatural Sciences and Engineering Research Council of CanadaCornell Center for Materials ResearchDefense Advanced Research Projects AgencyNational Institute of Food and AgricultureNational Science Foundation
KeywordsComputer scienceNatural language processing

Abstract

fetched live from OpenAlex

Developing prompt-based methods with Large Language Models (LLMs) requires making numerous decisions, which give rise to a combinatorial search problem over hyper-parameters. This exhaustive evaluation can be time-consuming and costly. In this paper, we propose an $\textit{adaptive}$ approach to explore this space. We are exploiting the fact that often only few samples are needed to identify clearly superior or inferior settings, and that many evaluation tests are highly correlated. We lean on multi-armed bandits to sequentially identify the next (method, validation sample)-pair to evaluate and utilize low-rank matrix factorization to fill in missing evaluations. We carefully assess the efficacy of our approach on several competitive benchmark problems and show that it can identify the top-performing method using only 5-15% of the typical resources -- resulting in 85-95% LLM cost savings. Our code is available at https://github.com/kilian-group/banditeval.

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)0.019
metaresearch head score (Gemma)0.095
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: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.019
Threshold uncertainty score0.099

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0190.095
Meta-epidemiology (narrow)0.0040.002
Meta-epidemiology (broad)0.0030.002
Bibliometrics0.0030.002
Science and technology studies0.0020.002
Scholarly communication0.0050.009
Open science0.0040.005
Research integrity0.0040.006
Insufficient payload (model declined to judge)0.0190.012

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 head0.096
GPT teacher head0.250
Teacher spread0.155 · 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
GenreEmpirical

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

Citations0
Published2024
Admission routes1
Has abstractyes

Explore more

Same venuearXiv (Cornell University)→Same topicNatural Language Processing Techniques→French-language works237,207→