Skip to content
conftrace_
2025 EMNLP EMNLP 2025

Command-A-Translate: Raising the Bar of Machine Translation with Difficulty Filtering

AbstractWe present Command A Translate, an LLMbased machine translation model built off Cohere’s Command A. It reaches state-of-the-art machine translation quality via direct preference optimization. Our meticulously designed data preparation pipeline emphasizes robust quality control and a novel difficulty filtering – a key innovation that distinguishes Command A Translate. Furthermore, we extend our model and participate at WMT with a system (CommandA-WMT) that uses two models and post-editing steps of step-by-step reasoning and limited Minimum Bayes Risk decoding.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

More from EMNLP 2025

All EMNLP 2025 papers →