发表机构
University of Illinois at Urbana-Champaign; Google DeepMind（伊利诺伊大学厄巴纳-香槟分校; 谷歌DeepMind）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究通过层次化元摘要框架分析大型推理模型在机器翻译中的推理轨迹，发现推理语言、长度和模式对翻译质量有复杂影响，提出应模型感知、长度感知和模式感知地控制推理。
AI 中文摘要
大型推理模型越来越多地使用中间轨迹进行机器翻译，但此类推理何时有益或有害仍不清楚。我们跨模型、语言、领域和数据集分析了推理轨迹，重点关注推理语言、长度和结构。我们发现最佳推理语言因模型而异，推理长度与质量呈非单调关系，且轨迹表现出重复的功能模式。为揭示这些模式，我们引入了层次化元摘要（HMS），这是一个可扩展的框架，无需预定义分类法即可归纳出粗粒度和细粒度的推理结构。HMS揭示了一种共享的组织结构——理解/规划、翻译/起草和精炼/验证——以及领域特定的差异。我们的结果表明，机器翻译中的推理应以模型感知、长度感知和模式感知的方式加以控制，而非统一鼓励。
英文摘要
Large Reasoning Models increasingly use intermediate traces for machine translation, but it remains unclear when such reasoning helps or hurts. We analyze reasoning traces across models, languages, domains, and datasets, focusing on reasoning language, length, and structure. We find that the best reasoning language is model-specific, reasoning length has a non-monotonic relationship with quality, and traces exhibit recurring functional patterns. To uncover these patterns, we introduce Hierarchical Meta-Summarization (HMS), a scalable framework that induces coarse- and fine-grained reasoning structures without predefined taxonomies. HMS reveals a shared organization--understanding/planning, translating/drafting, and refining/verifying--alongside domain-specific variation. Our results suggest that MT reasoning should be controlled in a model-aware, length-aware, and pattern-aware manner rather than uniformly encouraged.
CommentsAccepted to EMNLP 2026 Main
