mlsanityData to 14 Oct 2026

R1-T1: Fully Incentivizing Translation Capability in LLMs via Reasoning Learning

arXiv 2502.19735 ↗First posted 27 Feb 2025cs.CLcited by 21

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Despite recent breakthroughs in reasoning-enhanced large language models (LLMs) like DeepSeek-R1, incorporating inference-time reasoning into machine translation (MT), where human translators naturally employ structured, multi-layered reasoning chain-of-thoughts (CoTs), is yet underexplored. Existing methods either design a fixed CoT tailored for a specific MT sub-task (e.g., literature translation), or rely on synthesizing CoTs unaligned with humans and supervised fine-tuning (SFT) prone to overfitting, limiting their adaptability to diverse translation scenarios. This paper introduces R1-Translator (R1-T1), a novel framework to achieve inference-time reasoning for general MT via reinforcement learning (RL) with human-aligned CoTs comprising six common patterns. Our approach pioneers three innovations: (1) extending reasoning-based translation to broader MT scenarios (e.g., multilingual MT, domain MT) unseen in the training phase; (2) formalizing six expert-curated CoT templates that mirror hybrid human strategies like context-aware paraphrasing and back translation; and (3) enabling self-evolving CoT discovery through RL. Both human and automatic evaluation results indicate a steady translation performance improvement in a total of 10+ languages and 40+ translation directions on Flores-101 test set and four domain-specific MT tasks, especially on the languages unseen from training.

Key facts. Cited by 21 papers in the map (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 40 of its 82 references that are in the map. First posted on arXiv 27 Feb 2025.

Builds on

40 of 82 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Do Multilingual LLMs Think In English?21 Feb
  2. 2025Domaino1s: Guiding LLM Reasoning for Explainable Answers in High-Stakes Domains24 Jan
  3. 2024DRT: Deep Reasoning Translation via Long Chain-of-Thought23 Dec
  4. 2023Better Zero-Shot Reasoning with Role-Play Prompting15 Aug

Other references · 36

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2017Proximal Policy Optimization Algorithmscited by 15,215
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  5. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  6. 2024Qwen2.5 Technical Reportcited by 4,942
  7. 2024GPT-4o System Cardcited by 4,588
  8. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,312
  9. 2020COMET: A Neural Framework for MT Evaluationcited by 1,033
  10. 2025SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-trainingcited by 672
  11. 2021The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translationcited by 560
  12. 2021Experts, Errors, and Context: A Large-Scale Study of Human Evaluation for Machine Translationcited by 338
24 more
  1. 2023xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detectioncited by 265
  2. 2023Is ChatGPT A Good Translator? Yes With GPT-4 As The Enginecited by 176
  3. 2024Marco-o1: Towards Open Reasoning Models for Open-Ended Solutionscited by 144
  4. 2024O1 Replication Journey: A Strategic Progress Report -- Part 1cited by 143
  5. 2023Towards Making the Most of ChatGPT for Machine Translationcited by 138
  6. 2024Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsalcited by 118
  7. 2024Continual Pre-Training for Cross-Lingual LLM Adaptation: Enhancing Japanese Language Capabilitiescited by 111
  8. 2024Revisiting Catastrophic Forgetting in Large Language Model Tuningcited by 99
  9. 2023A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Modelscited by 89
  10. 2022On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgettingcited by 82
  11. 2024o1-Coder: an o1 Replication for Codingcited by 78
  12. 2024Adapting Large Language Models for Document-Level Machine Translationcited by 59
  13. 2023Benchmarking Machine Translation with Cultural Awarenesscited by 53
  14. 2025Understand, Solve and Translate: Bridging the Multilingual Mathematical Reasoning Gapcited by 43
  15. 2023PLUG: Leveraging Pivot Language in Cross-Lingual Instruction Tuningcited by 39
  16. 2024TEaR: Improving LLM-based Machine Translation with Systematic Self-Refinementcited by 39
  17. 2024X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scalecited by 36
  18. 2023ParroT: Translating during Chat using Large Language Models tuned with Human Translation and Feedbackcited by 34
  19. 2024TasTe: Teaching Large Language Models to Translate through Self-Reflectioncited by 27
  20. 2024Preliminary WMT24 Ranking of General MT Systems and LLMscited by 20
  21. 2024Can Automatic Metrics Assess High-Quality Translations?cited by 16
  22. 2024Retrieval-Augmented Machine Translation with Unstructured Knowledgecited by 9
  23. 2024Improving Language Models Trained on Translated Data with Continual Pre-Training and Dictionary Learning Analysiscited by 5
  24. 2024Gradable ChatGPT Translation Evaluationcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 14; 2026: 7.

21 papers.

Sort:

By area:

  1. 2025MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learningcited by 48
  2. 2025VerIF: Verification Engineering for Reinforcement Learning in Instruction Followingcited by 44
  3. 2025SSR-Zero: Simple Self-Rewarding Reinforcement Learning for Machine Translationcited by 13
  4. 2025An Efficient and Precise Training Data Construction Framework for Process-supervised Reward Model in Mathematical Reasoningcited by 12
  5. 2025ExTrans: Multilingual Deep Reasoning Translation via Exemplar-Enhanced Reinforcement Learningcited by 11
  6. 2025Seed LiveInterpret 2.0: End-to-end Simultaneous Speech-to-speech Translation with Your Voicecited by 9
  7. 2025DeepTrans: Deep Reasoning Translation via Reinforcement Learningcited by 8
  8. 2025How Well Do Large Reasoning Models Translate? A Comprehensive Evaluation for Multi-Domain Machine Translationcited by 5
  9. 2025TACTIC: Translation Agents with Cognitive-Theoretic Interactive Collaborationcited by 5
  10. 2025Test-Time Scaling of Reasoning Models for Machine Translationcited by 5
  11. 2026Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligencecited by 5
  12. 2025RIVAL: Reinforcement Learning with Iterative and Adversarial Optimization for Machine Translationcited by 4
9 more
  1. 2025LLM Reasoning for Machine Translation: Synthetic Data Generation over Thinking Tokenscited by 4
  2. 2025R-Log: Incentivizing Log Analysis Capability in LLMs via Reasoning-based Reinforcement Learningcited by 3
  3. 2026Chart Specification: Structural Representations for Incentivizing VLM Reasoning in Chart-to-Code Generationcited by 2
  4. 2025Chain-of-Thought Reasoning Improves Context-Aware Translation with Large Language Modelscited by 1
  5. 2026The GaoYao Benchmark: A Comprehensive Framework for Evaluating Multilingual and Multicultural Abilities of Large Language Modelscited by 1
  6. 2026Reasoning over Grammar: Can Synthetic Linguistic Reasoning Traces Enhance Low-Resource Machine Translation?cited by 0
  7. 2026Reasoning Before Translation: Enhancing Legal Machine Translation with Structured Reasoningcited by 0
  8. 2026Reasoning about In-Context Samples for Machine-Translationcited by 0
  9. 2026When Does Reasoning Help in Machine Translation? A Hierarchical Analysis of LRM Reasoning Tracescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Translation with Thought: Difficulty-Adaptive Reasoning via Reinforcement Learning for Multi-Domain Machine Translation
  2. 2025Please Translate Again: Two Simple Experiments on Whether Human-Like Reasoning Helps Translation
  3. 2025New Trends for Modern Machine Translation with Large Reasoning Models
  4. 2026Unlocking Reasoning Capability on Machine Translation in Large Language Models
  5. 2025RL of Thoughts: Navigating LLM Reasoning with Inference-time Reinforcement Learning
  6. 2026The Price of Reasoning: Cost-Quality Tradeoffs in Reinforcement Learning for Neural Machine Translation
  7. 2026Learning When to Translate for Multilingual Reasoning
  8. 2025RAST: Reasoning Activation in LLMs via Small-model Transfer