Translation with Thought: Difficulty-Adaptive Reasoning via Reinforcement Learning for Multi-Domain Machine Translation
带思考的翻译:面向多领域机器翻译的难度自适应推理强化学习方法
机构 * Institute of Artificial Intelligence, Xiamen University(厦门大学人工智能研究院) ; School of Informatics, Xiamen University(厦门大学信息学院) ; Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan (Xiamen University), Ministry of Culture and Tourism(文化和旅游部闽台非物质文化遗产数字化保护与智能处理重点实验室(厦门大学))
AI总结 该研究针对多领域机器翻译的难度差异挑战,提出TwT框架,经两阶段训练后,其7B和14B参数版本在翻译质量上优于更大的SOTA模型,且token使用量降低32%-60%。
Comments 34 pages, 17 figures, and 21 tables. Accepted to ACL 2026