Saved in:
Bibliographic Details
Main Authors: Issaka, Sheriff, Gonzalez, Erick Rosas, Liu, Lieqi, Agyei, Evans Kofi, Bandarkar, Lucas, Peng, Nanyun, Adelani, David Ifeoluwa, Guzmán, Francisco, Gabriel, Saadia
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.11778
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911382207725568
author Issaka, Sheriff
Gonzalez, Erick Rosas
Liu, Lieqi
Agyei, Evans Kofi
Bandarkar, Lucas
Peng, Nanyun
Adelani, David Ifeoluwa
Guzmán, Francisco
Gabriel, Saadia
author_facet Issaka, Sheriff
Gonzalez, Erick Rosas
Liu, Lieqi
Agyei, Evans Kofi
Bandarkar, Lucas
Peng, Nanyun
Adelani, David Ifeoluwa
Guzmán, Francisco
Gabriel, Saadia
contents The rapid proliferation of LLMs has created a critical evaluation paradox: while LLMs claim multilingual proficiency, comprehensive non-machine-translated benchmarks exist for fewer than 30 languages, leaving >98% of the world's 7,000 languages in an empirical void. Traditional benchmark construction faces scaling challenges such as cost, scarcity of domain experts, and data contamination. We evaluate the validity of a simpler alternative: can translation quality alone indicate a model's broader multilingual capabilities? Through systematic evaluation of 14 models (1B-72B parameters) across 9 diverse benchmarks and 7 translation metrics, we find that translation performance is a good indicator of downstream task success (e.g., Phi-4, median Pearson r: MetricX = 0.89, xCOMET = 0.91, SSA-COMET = 0.87). These results suggest that the representational abilities supporting faithful translation overlap with those required for multilingual understanding. Translation quality, thus emerges as a strong, inexpensive first-pass proxy of multilingual performance, enabling a translation-first screening with targeted follow-up for specific tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2601_11778
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Translation as a Scalable Proxy for Multilingual Evaluation
Issaka, Sheriff
Gonzalez, Erick Rosas
Liu, Lieqi
Agyei, Evans Kofi
Bandarkar, Lucas
Peng, Nanyun
Adelani, David Ifeoluwa
Guzmán, Francisco
Gabriel, Saadia
Computation and Language
Artificial Intelligence
The rapid proliferation of LLMs has created a critical evaluation paradox: while LLMs claim multilingual proficiency, comprehensive non-machine-translated benchmarks exist for fewer than 30 languages, leaving >98% of the world's 7,000 languages in an empirical void. Traditional benchmark construction faces scaling challenges such as cost, scarcity of domain experts, and data contamination. We evaluate the validity of a simpler alternative: can translation quality alone indicate a model's broader multilingual capabilities? Through systematic evaluation of 14 models (1B-72B parameters) across 9 diverse benchmarks and 7 translation metrics, we find that translation performance is a good indicator of downstream task success (e.g., Phi-4, median Pearson r: MetricX = 0.89, xCOMET = 0.91, SSA-COMET = 0.87). These results suggest that the representational abilities supporting faithful translation overlap with those required for multilingual understanding. Translation quality, thus emerges as a strong, inexpensive first-pass proxy of multilingual performance, enabling a translation-first screening with targeted follow-up for specific tasks.
title Translation as a Scalable Proxy for Multilingual Evaluation
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2601.11778