Proxylm: Predicting language model performance on multilingual tasks via proxy models
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F26%3AA2M3GYM9" target="_blank" >RIV/00216208:11320/26:A2M3GYM9 - isvavai.cz</a>
Result on the web
<a href="https://aclanthology.org/2025.findings-naacl.106/" target="_blank" >https://aclanthology.org/2025.findings-naacl.106/</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Proxylm: Predicting language model performance on multilingual tasks via proxy models
Original language description
Performance prediction is a method to estimate the performance of Language Models (LMs) on various Natural Language Processing (NLP) tasks, mitigating computational costs associated with model capacity and data for fine-tuning. Our paper presents ProxyLM, a scalable task- and language-agnostic framework designed to predict the performance of LMs using proxy models. These proxy models act as surrogates, approximating the performance of the LM of interest. By leveraging these proxy models, ProxyLM significantly reduces computational overhead in task evaluations, achieving up to a 37.08x speedup over traditional methods, even with our smallest proxy models. Our results across multiple multilingual NLP tasks and various robustness tests demonstrate that ProxyLM not only adapts well to previously unseen languages in pre-trained LMs, but also generalizes effectively across different datasets, outperforming the state-of-the-art by at least 1.78x in terms of root-mean-square error (RMSE).
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
—
Others
Publication year
2025
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Findings of the Association for Computational Linguistics: NAACL 2025
ISBN
979-8-89176-195-7
ISSN
—
e-ISSN
—
Number of pages
31
Pages from-to
1981-2011
Publisher name
—
Place of publication
—
Event location
Albuquerque, New Mexico
Event date
Jan 1, 2026
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—