SoT：结构化思维提示引导大语言模型的多语言推理
SoT: Structured-of-Thought Prompting Guides Multilingual Reasoning in Large Language Models
AI总结：
针对非高资源语言下大语言模型多语言推理能力不足的问题，提出无需训练的结构化思维提示方法SoT，通过两步变换实现跨语言一致推理，在多基准上优于强基线且可兼容其他免训练策略。
摘要：
近期的发展使得大语言模型（LLMs）能够通过深度思考执行复杂推理任务。然而，受资源限制，推理能力尚未成功迁移到非高资源语言，这类语言在多语言推理任务中表现不佳。为此，我们提出结构化思维（Structured-of-Thought, SoT），这是一种无需训练的方法，通过两步变换提升多语言推理性能：语言思维变换和结构化知识变换。SoT方法将特定语言的语义信息转换为与语言无关的结构化表示，使模型能更精准地理解不同语言的查询。此外，SoT能有效引导LLMs进行更聚焦的推理，在处理跨语言表达差异时保持一致的底层推理路径。实验结果表明，在适配多种LLM骨干模型时，SoT在多个多语言推理基准上优于多个强基线方法。它还可与其他无需训练的策略结合以实现进一步提升。我们的代码可在https://github.com/Cherry-qwq/SoT获取。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
