Translation with Thought: Difficulty-Adaptive Reasoning via Reinforcement Learning for Multi-Domain Machine Translation

• URL: http://arxiv.org/abs/2607.29287v1
• Date: Fri, 31 Jul 2026 10:59:39 GMT
• Title: Translation with Thought: Difficulty-Adaptive Reasoning via Reinforcement Learning for Multi-Domain Machine Translation
• Abstract summary: We propose TwT (Translation with Thought), a resource-rational framework that learns to modulate inference between intuitive and deliberate reasoning.<n>TwT is trained in two stages: (1) supervised fine-tuning on difficulty-aware long chain-of-thought traces distilled from DeepSeek-R1 and rewritten by GPT-4o to reflect human-like reasoning economy, and (2) reinforcement learning with a hybrid reward to optimize translation quality and reasoning efficiency.
• Score: 19.884019376360456
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-domain machine translation (MDMT) poses a unique challenge due to varying levels of linguistic complexity across domains. Inspired by human translators' ability to adapt reasoning effort based on difficulty, we propose TwT (Translation with Thought), a resource-rational framework that learns to modulate inference between intuitive and deliberate reasoning. TwT is trained in two stages: (1) supervised fine-tuning on difficulty-aware long chain-of-thought traces distilled from DeepSeek-R1 and rewritten by GPT-4o to reflect human-like reasoning economy, and (2) reinforcement learning with a hybrid reward to optimize translation quality and reasoning efficiency. Evaluated on 15 benchmarks spanning in-domain and out-of-domain settings, as well as 3 seen and 59 unseen languages, with ablations across three backbone models, TwT-7B and TwT-14B outperform much larger SOTA reasoning models in translation quality, while reducing token usage by 32--60\%. These results confirm that aligning translation behavior with cognitive principles enables robust generalization, high translation quality, and efficient reasoning in MDMT.

Related papers

• ReflectMT: Internalizing Reflection for Efficient and High-Quality Machine Translation [63.89730738735446]
  We propose ReflectMT, a two-stage reflection internalization algorithm for machine translation.<n>Our approach develops the model's "translate-reflect-refine" capability through reinforcement learning.<n> Experimental results on datasets such as WMT24 demonstrate that our model's first-pass translations during inference outperform multi-step reasoning LRMs.
  arXiv  Detail & Related papers  (2026-04-21T06:48:41Z)
• Incentivizing Parametric Knowledge via Reinforcement Learning with Verifiable Rewards for Cross-Cultural Entity Translation [68.85147984815778]
  We propose EA-RLVR (Entity-Anchored Reinforcement Learning with Verifiable Rewards) to incentivize the effective use of parametric knowledge.<n>EA-RLVR anchors supervision on a verifiable, entity-level reward signal and incorporates lightweight structural gates to stabilize optimization.<n>We evaluate EA-RLVR on XC-Translate and observe consistent improvements in both entity translation accuracy and out-of-domain generalization.
  arXiv  Detail & Related papers  (2026-04-18T07:15:43Z)
• On the Role of Reasoning Patterns in the Generalization Discrepancy of Long Chain-of-Thought Supervised Fine-Tuning [63.41902113656453]
  Supervised Fine-Tuning (SFT) on long Chain-of-Thought (CoT) trajectories has become a pivotal phase in building large reasoning models.<n>We conduct a comparative study using two sources of verified CoT trajectories generated by two competing models.<n>We find that SFT on textttDeepSeek-R1-0528 data achieves remarkably lower training loss, yet exhibits significantly worse generalization performance.
  arXiv  Detail & Related papers  (2026-04-02T07:00:54Z)
• Unlocking Reasoning Capability on Machine Translation in Large Language Models [57.60641851466707]
  Reasoning-oriented large language models (RLMs) achieve strong gains on tasks such as mathematics and coding by generating explicit intermediate reasoning.<n>We systematically evaluate several open- and closed-weights RLMs on the WMT24++ benchmark.<n>We find that enabling explicit reasoning consistently degrades translation quality across languages and models.
  arXiv  Detail & Related papers  (2026-02-16T14:05:59Z)
• Test-Time Scaling of Reasoning Models for Machine Translation [16.317481079574065]
  Test-time scaling (TTS) has enhanced the performance of Reasoning Models (RMs) on various tasks such as math and coding.<n>This paper investigates whether increased inference-time computation improves translation quality.
  arXiv  Detail & Related papers  (2025-10-07T21:15:18Z)
• ReaLM: Reflection-Enhanced Autonomous Reasoning with Small Language Models [76.28894983518164]
  Small Language Models (SLMs) are a cost-effective alternative to Large Language Models (LLMs)<n>They often struggle with complex reasoning due to their limited capacity and a tendency to produce mistakes or inconsistent answers.<n>We introduce ReaLM, a reinforcement learning framework for robust and self-sufficient reasoning in vertical domains.
  arXiv  Detail & Related papers  (2025-08-17T14:50:23Z)
• R1-T1: Fully Incentivizing Translation Capability in LLMs via Reasoning Learning [23.721573333602677]
  This paper introduces R1-Translator (R1-T1), a novel framework to achieve inference-time reasoning for general machine translation (MT) via reinforcement learning (RL)<n>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.
  arXiv  Detail & Related papers  (2025-02-27T03:57:00Z)
• LLM-based Translation Inference with Iterative Bilingual Understanding [52.46978502902928]
  We propose a novel Iterative Bilingual Understanding Translation method based on the cross-lingual capabilities of large language models (LLMs)<n>The cross-lingual capability of LLMs enables the generation of contextual understanding for both the source and target languages separately.<n>The proposed IBUT outperforms several strong comparison methods.
  arXiv  Detail & Related papers  (2024-10-16T13:21:46Z)
• Large Language Model for Multi-Domain Translation: Benchmarking and Domain CoT Fine-tuning [55.107329995417786]
  Large language models (LLMs) have demonstrated impressive general understanding and generation abilities. We establish a benchmark for multi-domain translation, featuring 25 German$Leftrightarrow$English and 22 Chinese$Leftrightarrow$English test sets. We propose a domain Chain of Thought (CoT) fine-tuning technique that utilizes the intrinsic multi-domain intelligence of LLMs to improve translation performance.
  arXiv  Detail & Related papers  (2024-10-03T16:15:04Z)
• Exploiting Curriculum Learning in Unsupervised Neural Machine Translation [28.75229367700697]
  We propose a curriculum learning method to gradually utilize pseudo bi-texts based on their quality from multiple granularities. Experimental results on WMT 14 En-Fr, WMT 16 En-De, WMT 16 En-Ro, and LDC En-Zh translation tasks demonstrate that the proposed method achieves consistent improvements with faster convergence speed.
  arXiv  Detail & Related papers  (2021-09-23T07:18:06Z)

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.