TwT:难度自适应推理的多领域机器翻译框架
Translation with Thought: Difficulty-Adaptive Reasoning via Reinforcement Learning for Multi-Domain Machine Translation
这个TwT框架让翻译模型根据难度动态调整思考量,7B和14B的小模型打过大模型,token还省了30%到60%,做多领域翻译的可以看看。
TwT(Translation with Thought)是一个难度自适应的多领域机器翻译框架,通过强化学习在直觉与深思推理间动态切换。
该模型先利用DeepSeek-R1蒸馏并由GPT-4o重写的长思维链进行监督微调,再通过混合奖励优化翻译质量与推理效率。在15个基准、3种已见语言和59种未见语言上,TwT-7B和TwT-14B的翻译质量超过更大的SOTA推理模型,同时token用量减少32%至60%。
Translation with Thought: Difficulty-Adaptive Reasoning via Reinforcement Learning for Multi-Domain Machine Translation
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.
This report is categorized under AITOP's "Papers" desk. Key entities and technical topics under continuous tracking include TwT, DeepSeek-R1, GPT-4o, machine translation.
Primary source verification: published directly by arXiv: DeepSeek with first-party authority.