Quantifying Language Disparities in Multilingual Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hu, Songbo, Vulić, Ivan, Korhonen, Anna
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916914094145536
author Hu, Songbo
Vulić, Ivan
Korhonen, Anna
author_facet Hu, Songbo
Vulić, Ivan
Korhonen, Anna
contents Results reported in large-scale multilingual evaluations are often fragmented and confounded by factors such as target languages, differences in experimental setups, and model choices. We propose a framework that disentangles these confounding variables and introduces three interpretable metrics--the performance realisation ratio, its coefficient of variation, and language potential--enabling a finer-grained and more insightful quantification of actual performance disparities across both (i) models and (ii) languages. Through a case study of 13 model variants on 11 multilingual datasets, we demonstrate that our framework provides a more reliable measurement of model performance and language disparities, particularly for low-resource languages, which have so far proven challenging to evaluate. Importantly, our results reveal that higher overall model performance does not necessarily imply greater fairness across languages.
format Preprint
id arxiv_https___arxiv_org_abs_2508_17162
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Quantifying Language Disparities in Multilingual Large Language Models
Hu, Songbo
Vulić, Ivan
Korhonen, Anna
Computation and Language
Results reported in large-scale multilingual evaluations are often fragmented and confounded by factors such as target languages, differences in experimental setups, and model choices. We propose a framework that disentangles these confounding variables and introduces three interpretable metrics--the performance realisation ratio, its coefficient of variation, and language potential--enabling a finer-grained and more insightful quantification of actual performance disparities across both (i) models and (ii) languages. Through a case study of 13 model variants on 11 multilingual datasets, we demonstrate that our framework provides a more reliable measurement of model performance and language disparities, particularly for low-resource languages, which have so far proven challenging to evaluate. Importantly, our results reveal that higher overall model performance does not necessarily imply greater fairness across languages.
title Quantifying Language Disparities in Multilingual Large Language Models
topic Computation and Language
url https://arxiv.org/abs/2508.17162