Translation as a Scalable Proxy for Multilingual Evaluation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _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 |