Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets

TL;DR

This paper introduces an automated, scalable translation pipeline for benchmarks that maintains semantic integrity, improving multilingual evaluation accuracy for large language models across eight European languages.

Contribution

The work presents a novel translation framework utilizing test-time compute scaling and multi-round ranking to produce high-quality multilingual benchmarks, preserving task structure and linguistic nuances.

Findings

Translations outperform existing resources in quality metrics.

Framework enables accurate multilingual model evaluation.

Releases include tools and benchmarks for community use.

Abstract

The reliability of multilingual Large Language Model (LLM) evaluation is currently compromised by the inconsistent quality of translated benchmarks. Existing resources often suffer from semantic drift and context loss, which can lead to misleading performance metrics. In this work, we present a fully automated framework designed to address these challenges by enabling scalable, high-quality translation of datasets and benchmarks. We demonstrate that adapting test-time compute scaling strategies, specifically Universal Self-Improvement (USI) and our proposed multi-round ranking method, T-RANK, allows for significantly higher quality outputs compared to traditional pipelines. Our framework ensures that benchmarks preserve their original task structure and linguistic nuances during localization. We apply this approach to translate popular benchmarks and datasets into eight Eastern and Southern European languages (Ukrainian, Bulgarian, Slovak, Romanian, Lithuanian, Estonian, Turkish, Greek). Evaluations using both reference-based metrics and LLM-as-a-judge show that our translations surpass existing resources, resulting in more accurate downstream model assessment. We release both the framework and the improved benchmarks to facilitate robust and reproducible multilingual AI development.