mlsanityData to 14 Oct 2026

Discovering Translation-Worthy Languages with E-Values

arXiv 2609.06593 ↗First posted 6 Sep 2026cs.CL cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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 languages per dataset by 0.05. On SIB-200 and MASSIVE, the router selects translation for 4 of 15 languages and 14 of 15 locales, improving held-out accuracy over direct classification by 8.14 and 16.70 percentage points, respectively. All 28 decisions remain stable across 50 outcome-independent orderings and relative to the per-group threshold. Our results demonstrate that paired e-processes enable statistically controlled, anytime-valid, and auditable multilingual classification routing.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 14 of its 16 references that are in the map. First posted on arXiv 6 Sep 2026.

Builds on

14 of 16 references.

References · 14

  1. 2024RouteLLM: Learning to Route LLMs with Preference Datacited by 682
  2. 2022Game-theoretic statistics and safe anytime-valid inferencecited by 155
  3. 2023SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialectscited by 152
  4. 2022MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languagescited by 146
  5. 2019Safe Testingcited by 101
  6. 2023Revisiting Machine Translation for Cross-lingual Classificationcited by 41
  7. 2020FrugalML: How to Use ML Prediction APIs More Accurately and Cheaplycited by 33
  8. 2020Confidence sequences for sampling without replacementcited by 23
  9. 2026PACE: Anytime-Valid Acceptance Tests for Self-Evolving Agentscited by 13
  10. 2021Comparing Sequential Forecasterscited by 8
  11. 2026Resolution Diagnostics for Paired LLM Evaluationcited by 7
  12. 2026RouteLMT: Learned Sample Routing for Hybrid LLM Translation Deploymentcited by 2
2 more
  1. 2026No One Fits All: From Fixed Prompting to Learned Routing in Multilingual LLMscited by 1
  2. 2026A Cost-Efficient Routing Pipeline for Multilingual Short-Text Classification Using Small Language Modelscited by 1

Built on by

Not cited yet.