TranslateGemma Technical Report

• URL: http://arxiv.org/abs/2601.09012v3
• Date: Mon, 19 Jan 2026 09:52:02 GMT
• Title: TranslateGemma Technical Report
• Authors: Mara Finkelstein, Isaac Caswell, Tobias Domhan, Jan-Thorsten Peter, Juraj Juraska, Parker Riley, Daniel Deutsch, Geza Kovacs, Cole Dilanni, Colin Cherry, Eleftheria Briakou, Elizabeth Nielsen, Jiaming Luo, Kat Black, Ryan Mullins, Sweta Agrawal, Wenda Xu, Erin Kats, Stephane Jaskiewicz, Markus Freitag, David Vilar,
• Abstract summary: We present TranslateGemma, a suite of open machine translation models based on the Gemma 3 foundation models.<n>We show consistent and substantial gains over the baseline Gemma 3 models across all sizes.<n>We also show that TranslateGemma models retain strong multimodal capabilities, with enhanced performance on the Vistra image translation benchmark.
• Score: 39.30046490326195
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present TranslateGemma, a suite of open machine translation models based on the Gemma 3 foundation models. To enhance the inherent multilingual capabilities of Gemma 3 for the translation task, we employ a two-stage fine-tuning process. First, supervised fine-tuning is performed using a rich mixture of high-quality large-scale synthetic parallel data generated via state-of-the-art models and human-translated parallel data. This is followed by a reinforcement learning phase, where we optimize translation quality using an ensemble of reward models, including MetricX-QE and AutoMQM, targeting translation quality. We demonstrate the effectiveness of TranslateGemma with human evaluation on the WMT25 test set across 10 language pairs and with automatic evaluation on the WMT24++ benchmark across 55 language pairs. Automatic metrics show consistent and substantial gains over the baseline Gemma 3 models across all sizes. Notably, smaller TranslateGemma models often achieve performance comparable to larger baseline models, offering improved efficiency. We also show that TranslateGemma models retain strong multimodal capabilities, with enhanced performance on the Vistra image translation benchmark. The release of the open TranslateGemma models aims to provide the research community with powerful and adaptable tools for machine translation.

Related papers

• Scaling Model and Data for Multilingual Machine Translation with Open Large Language Models [38.626788948945844]
  We present a study of open large language models (LLMs) for multilingual machine translation (MT) across a range of languages.<n>We develop MiLMMT-46, which achieves top-tier multilingual translation performance across 46 languages.
  arXiv  Detail & Related papers  (2026-02-12T13:56:02Z)
• Seed-X: Building Strong Multilingual Translation LLM with 7B Parameters [53.59868121093848]
  We introduce Seed-X, a family of open-source language models (LLMs) with 7B parameter size.<n>The base model is pre-trained on a diverse, high-quality dataset encompassing both monolingual and bilingual content across 28 languages.<n>The instruct model is then finetuned to translate by Chain-of-Thought (CoT) reasoning and further enhanced through reinforcement learning (RL) to achieve better generalization across diverse language pairs.
  arXiv  Detail & Related papers  (2025-07-18T03:19:43Z)
• Trans-Zero: Self-Play Incentivizes Large Language Models for Multilingual Translation Without Parallel Data [64.4458540273004]
  We propose a self-play framework that leverages only monolingual data and the intrinsic multilingual knowledge of Large Language Models (LLMs)<n>Experiments demonstrate that this approach not only matches the performance of models trained on large-scale parallel data but also excels in non-English translation directions.
  arXiv  Detail & Related papers  (2025-04-20T16:20:30Z)
• Multilingual Machine Translation with Open Large Language Models at Practical Scale: An Empirical Study [13.409987421121405]
  GemmaX2-28 is a 9B model achieving top-tier multilingual translation performance across 28 languages.<n>GemmaX2-28 consistently outperforms the state-of-the-art (SOTA) models such as TowerInstruct and XALMA.
  arXiv  Detail & Related papers  (2025-02-04T16:57:03Z)
• Efficient Machine Translation with a BiLSTM-Attention Approach [0.0]
  This paper proposes a novel Seq2Seq model aimed at improving translation quality while reducing the storage space required by the model. The model employs a Bidirectional Long Short-Term Memory network (Bi-LSTM) as the encoder to capture the context information of the input sequence. Compared to the current mainstream Transformer model, our model achieves superior performance on the WMT14 machine translation dataset.
  arXiv  Detail & Related papers  (2024-10-29T01:12:50Z)
• Towards Zero-Shot Multimodal Machine Translation [64.9141931372384]
  We propose a method to bypass the need for fully supervised data to train multimodal machine translation systems.<n>Our method, called ZeroMMT, consists in adapting a strong text-only machine translation (MT) model by training it on a mixture of two objectives.<n>To prove that our method generalizes to languages with no fully supervised training data available, we extend the CoMMuTE evaluation dataset to three new languages: Arabic, Russian and Chinese.
  arXiv  Detail & Related papers  (2024-07-18T15:20:31Z)
• MTUncertainty: Assessing the Need for Post-editing of Machine Translation Outputs by Fine-tuning OpenAI LLMs [6.822926897514793]
  TQE is critical in assessing both machine translation (MT) and human translation (HT) quality without reference translations. This work examines whether the state-of-the-art large language models (LLMs) can be used for this purpose. We take OpenAI models as the best state-of-the-art technology and approach TQE as a binary classification task.
  arXiv  Detail & Related papers  (2023-07-31T21:13:30Z)
• Unified Model Learning for Various Neural Machine Translation [63.320005222549646]
  Existing machine translation (NMT) studies mainly focus on developing dataset-specific models. We propose a versatile'' model, i.e., the Unified Model Learning for NMT (UMLNMT) that works with data from different tasks. OurNMT results in substantial improvements over dataset-specific models with significantly reduced model deployment costs.
  arXiv  Detail & Related papers  (2023-05-04T12:21:52Z)
• The YiTrans End-to-End Speech Translation System for IWSLT 2022 Offline Shared Task [92.5087402621697]
  This paper describes the submission of our end-to-end YiTrans speech translation system for the IWSLT 2022 offline task. The YiTrans system is built on large-scale pre-trained encoder-decoder models. Our final submissions rank first on English-German and English-Chinese end-to-end systems in terms of the automatic evaluation metric.
  arXiv  Detail & Related papers  (2022-06-12T16:13:01Z)
• Supervised Visual Attention for Simultaneous Multimodal Machine Translation [47.18251159303909]
  We propose the first Transformer-based simultaneous machine translation (MMT) architecture. We extend this model with an auxiliary supervision signal that guides its visual attention mechanism using labelled phrase-region alignments. Our results show that supervised visual attention consistently improves the translation quality of the MMT models.
  arXiv  Detail & Related papers  (2022-01-23T17:25:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.