@InProceedings{kocmi-EtAl:2026:wmt2,
  author    = {Kocmi, Tom  and  Berard, Alexandre  and  Blunsom, Phil  and  Cahyawijaya, Samuel  and  Cassini, Shaun Rafael  and  de Gibert, Ona  and  Gomez, Aidan  and  Govindarajan, Nithya  and  Kiyono, Shun  and  Lasche, Olivia  and  Rogers, Lawrence  and  Marchisio, Kelly  and  Moghe, Nikita  and  More, Yash  and  Moran-Hidalgo, Camila  and  Nan, Yiyang  and  Sachs, Michael  and  Starostina, Trisha  and  van Stigt, Daan  and  Rarrick, Spencer Taylor  and  Vincent, Sebastian  and  Zhang, Ivan  and  Frosst, Nicholas},
  title     = {North Small Translate: Advanced Cost-Effective Translation (Cohere CAT+)},
  booktitle      = {Proceedings of the Eleventh Conference on Machine Translation},
  month          = {October},
  year           = {2026},
  address        = {Budapest, Hungary},
  publisher      = {Association for Computational Linguistics},
  pages     = {1312--1324},
  abstract  = {We present North Small Translate, an open-weight, LLM-based machine translation (MT) model with instruction-following capabilities built on the same foundation as Cohere's Command A Plus, a mixture-of-experts architecture with 25 billion active parameters out of 218 billion total parameters. North Small Translate is trained using difficulty sampling to obtain challenging documents and a five-step training protocol combining supervised fine-tuning, direct preference optimization, and online reinforcement learning. We prioritized throughput through a non-reasoning base model and supplemented with optional agentic capabilities to unlock translation quality gains. North Small Translate is trained to perform MT-related tasks, including post-editing and quality estimation, as well as related tasks such as general instruction following. The model achieves top MT performance across 50 languages in the class of models under 1T parameters, with no need to run expensive reasoning at inference time.},
  url       = {https://aclanthology.org/2026.wmt-1.70}
}