Proxylm: Predicting language model performance on multilingual tasks via proxy models

Kód výsledku v 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>

Výsledek na webu

<a href="https://aclanthology.org/2025.findings-naacl.106/" target="_blank" >https://aclanthology.org/2025.findings-naacl.106/</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Proxylm: Predicting language model performance on multilingual tasks via proxy models

Popis výsledku v původním jazyce

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).

Název v anglickém jazyce

Proxylm: Predicting language model performance on multilingual tasks via proxy models

Popis výsledku anglicky

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).

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

—

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Findings of the Association for Computational Linguistics: NAACL 2025

ISBN

979-8-89176-195-7

ISSN

—

e-ISSN

—

Počet stran výsledku

31

Strana od-do

1981-2011

Název nakladatele

—

Místo vydání

—

Místo konání akce

Albuquerque, New Mexico

Datum konání akce

1. 1. 2026

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—