SOURCE-LINKED INTELLIGENCE

TransClean: A Benchmark for Detecting and Extracting Clean Translations from Large Language Model Outputs

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

Large language models (LLMs) are increasingly used for machine translation, yet their outputs often contain additional text beyond the translation itself, such as language labels, explanations or bilingual repetitions, which we term translation noise. Despite its prevalence, this problem lacks dedicated benchmarks and systematic study. We analyze over 790,000 translation outputs from 12 LLMs across 22 language pairs (LPs) and identify 12 recurring noise patterns, which we group into formatting and content noise. Building on the observed patterns, we construct TransClean, a controlled benchmark

Read original source ↗ Open in workspace

recordType

paper

region

Global