SOURCE-LINKED INTELLIGENCE

Discovering Translation-Worthy Languages with E-Values

arXiv · AI, language, vision and robotics · article · Sep 6, 2026 · UTC

Choosing when to translate multilingual documents is a central routing problem in text classification: translation can improve predictions for some languages while degrading others or adding unnecessary computation. Uniform translation and heuristic language tiers do not provide statistically controlled route selection. We introduce a language-level router based on paired e-processes that continuously compares direct and translation-assisted classification before freezing a routing policy. A familywise-controlled threshold of 280 bounds the probability of any false route across 14 eligible lan

Read original source ↗ Open in workspace

recordType

paper

region

Global