让大模型跨语言推理更准，无需训练就能提升多语言思维能力。
SoT: Structured-of-Thought Prompting Guides Multilingual Reasoning in Large Language Models
- 通过语言思维与知识结构转换，将语言特有信息转为通用结构表示。
- 在多个多语言推理基准上超越强基线，适配不同大模型架构。
- 无需训练，可与其它无训练方法结合，适合多语言应用开发者。
近期研究使大语言模型（LLMs）能进行复杂推理，但资源匮乏的非高资源语言中推理能力难以迁移，限制了多语言推理发展。为此，我们提出无需训练的结构化思维（SoT）方法，通过语言思维转换和结构化知识转换两步实现：将语言特异性语义信息转化为语言无关的结构化表示，使模型更精准理解多语言查询；同时引导模型保持一致的深层推理路径，应对表达形式的跨语言差异。实验表明，SoT在多个多语言推理基准上优于多种强基线，适用于不同大模型主干，并可与其他无训练策略融合以进一步提升性能。代码已开源。
原文摘要 · Abstract (English)
Recent developments have enabled Large Language Models (LLMs) to engage in complex reasoning tasks through deep thinking. However, the capacity of reasoning has not been successfully transferred to non-high-resource languages due to resource constraints, which struggles with multilingual reasoning tasks. To this end, we propose Structured-of-Thought (SoT), a training-free method that improves the performance on multilingual reasoning through a multi-step transformation: Language Thinking Transformation and Structured Knowledge Transformation. The SoT method converts language-specific semantic information into language-agnostic structured representations, enabling the models to understand the query in different languages more sophisticated. Besides, SoT effectively guides LLMs toward more concentrated reasoning to maintain consistent underlying reasoning pathways when handling cross-lingual variations in expression. Experimental results demonstrate that SoT outperforms several strong baselines on multiple multilingual reasoning benchmarks when adapting to various backbones of LLMs. It can also be integrated with other training-free strategies for further improvements. Our code is available at https://github.com/Cherry-qwq/SoT.
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。