mlsanityData to 7 Oct 2026

Scaling Model and Data for Multilingual Machine Translation with Open Large Language Models

arXiv 2602.11961 ↗First posted 12 Feb 2026cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

Open large language models (LLMs) have demonstrated improving multilingual capabilities in recent years. In this paper, we present a study of open LLMs for multilingual machine translation (MT) across a range of languages, and investigate the effects of model scaling and data scaling when adapting open LLMs to multilingual MT through continual pretraining and instruction finetuning. Based on the Gemma3 model family, we develop MiLMMT-46, which achieves top-tier multilingual translation performance across 46 languages. Extensive experiments show that MiLMMT-46 consistently outperforms recent state-of-the-art (SOTA) models, including Seed-X, HY-MT-1.5, and TranslateGemma, and achieves competitive performance with strong proprietary systems such as Google Translate and Gemini 3 Pro. Models are released at https://huggingface.co/collections/xiaomi-research/milmmt-46. Codes are released at https://github.com/xiaomi-research/gemmax.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 16 of its 36 references that are in the map. First posted on arXiv 12 Feb 2026.

Builds on

16 of 36 references.

References · 16

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  2. 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,928
  3. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
  4. 2024LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Modelscited by 1,442
  5. 2020COMET: A Neural Framework for MT Evaluationcited by 1,024
  6. 2020The State and Fate of Linguistic Diversity and Inclusion in the NLP Worldcited by 789
  7. 2021The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translationcited by 556
  8. 2023xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detectioncited by 260
  9. 2024Tower: An Open Multilingual Large Language Model for Translation-Related Taskscited by 205
  10. 2023Scaling up COMETKIWI: Unbabel-IST 2023 Submission for the Quality Estimation Shared Taskcited by 88
  11. 2025WMT24++: Expanding the Language Coverage of WMT24 to 55 Languages & Dialectscited by 79
  12. 2025Tower+: Bridging Generality and Translation Specialization in Multilingual LLMscited by 40
4 more
  1. 2025Multilingual Machine Translation with Open Large Language Models at Practical Scale: An Empirical Studycited by 38
  2. 2024X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scalecited by 36
  3. 2025BOUQuET: dataset, Benchmark and Open initiative for Universal Quality Evaluation in Translationcited by 21
  4. 2025DCAD-2000: A Multilingual Dataset across 2000+ Languages with Data Cleaning as Anomaly Detectioncited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Parameter- and Bandwidth-Efficient Edge--cloud Many-to-Many Speech-to-Text Translationcited by 0
  2. 2026AlignAtt4LLM: Fast AlignAtt for Decoder-Only LLMs at IWSLT 2026 Simultaneous Speech Translation Taskcited by 0
  3. 2026Reference-Free Post-Training of Open Large Language Models for Multilingual Machine Translationcited by 0
  4. 2026Reference-Grounded Data Curation for Instruction-Following Thai-English Machine Translationcited by 0