让翻译推理保留原始问题，显著提升多语言问答准确率。
Multilingual Reasoning Cascades Need More Context
- 在翻译链末尾加入原始问题和推理过程作为上下文
- 跨9个基准、285种语言，开放生成任务表现明显提升
- 无需训练，对低资源语言尤其有效，适合部署使用
多语言推理的翻译级联方法将查询翻译成英语进行推理，再译回原语言。该方法虽具竞争力，但结构上信息损失严重，因各阶段会丢弃后续步骤所需的文化背景、语体及消歧线索。本文提出一种简单且无需训练的改进：在最终翻译模块中引入原始问题、英文翻译后的查询以及推理轨迹作为上下文。我们在包含多种任务类型的九个多语言基准上评估，涵盖三种主干模型和285种高、中、低资源语言，结果显示开放生成任务在各类模型与资源条件下均有显著提升。研究发现，原始语言问题提供了最主要的有益上下文。本工作强调需优化机器翻译级联中的信息流以减少误差传播，并提供了一个简单可行的默认策略：将用户原始问题保留在流程末端。
原文摘要 · Abstract (English)
Translation cascades for reasoning translate the query from another language to English, reason in English, and translate the answer back to the original language. This is a competitive approach to multilingual reasoning, but structurally lossy, since each stage discards information later stages may need, including cues for cultural grounding, register, and disambiguation. We examine the benefits of a simple and training-free intervention: a context-aware translation cascade, which additionally provides the original question, the English translated question, and the reasoning trace to the context of the final translation module. We evaluate gains across nine multilingual benchmarks including various task types, three backbone models, and 285 high-, mid-, and low-resource languages, and demonstrate strong gains for open-ended generation across models and resource regimes. We show that the original language question carries most of the beneficial context. Our study emphasizes the need to better design information flow in machine translation cascades for mitigating error propagation, and provides a simple and actionable default strategy: preserve the original user question until the end of the pipeline.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。