mlsanityData to 14 Oct 2026

North Small Translate: Advanced Cost-Effective Translation (Cohere CAT+)

arXiv 2609.13916 ↗First posted 12 Sep 2026cs.CLcited by 0

On the map: Mixture-of-experts → MoE large language models

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in MoE large language models, one of 12 directions in Mixture-of-experts. Builds on 13 of its 29 references that are in the map. First posted on arXiv 12 Sep 2026.

Builds on

13 of 29 references.

References · 13

  1. 2017Attention Is All You Needcited by 60,361
  2. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  3. 2026GLM-5: from Vibe Coding to Agentic Engineeringcited by 587
  4. 2023Large Language Models Are State-of-the-Art Evaluators of Translation Qualitycited by 420
  5. 2023xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detectioncited by 265
  6. 2021High Quality Rather than High Model Probability: Minimum Bayes Risk Decoding with Neural Metricscited by 104
  7. 2024MetricX-24: The Google Submission to the WMT 2024 Metrics Shared Taskcited by 93
  8. 2025WMT24++: Expanding the Language Coverage of WMT24 to 55 Languages & Dialectscited by 79
  9. 2023Ties Matter: Meta-Evaluating Modern Metrics with Pairwise Accuracy and Tie Calibrationcited by 74
  10. 2024Error Span Annotation: A Balanced Approach for Human Evaluation of Machine Translationcited by 62
  11. 2025Command A: An Enterprise-Ready Large Language Modelcited by 59
  12. 2024Guiding Large Language Models to Post-Edit Machine Translation with Error Annotationscited by 22
1 more
  1. 2024xTower: A Multilingual LLM for Explaining and Correcting Translation Errorscited by 17

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024From LLM to NMT: Advancing Low-Resource Machine Translation with Claude
  2. 2026Translate-R1: Cost-Aware Translation Tool Use via Reinforcement Learning
  3. 2025Bridging the Linguistic Divide: A Survey on Leveraging Large Language Models for Machine Translation
  4. 2025MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning
  5. 2026Improving Low-Resource Machine Translation via Round-Trip Reinforcement Learning
  6. 2024MT-PATCHER: Selective and Extendable Knowledge Distillation from Large Language Models for Machine Translation
  7. 2026Extracting Small Translation Specialists from LLMs by Aggressively Pruning Experts
  8. 2026CAT-Translate: Building Compact Open-Source Models for Japanese-English Translation