arXiv 2310.147992023-10-23cs.CLcs.AI

跨语言提示：改进跨语言的零样本思维链推理

Cross-lingual Prompting: Improving Zero-shot Chain-of-Thought Reasoning across Languages

Central South University（中南大学）；Harbin Institute of Technology（哈尔滨工业大学）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））

Libo Qin, Qiguang Chen, Fuxuan Wei, Shijue Huang, Wanxiang Che

备注：: Accepted at EMNLP2023 Main Conference

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对零样本思维链推理局限于单一语言的问题，提出跨语言提示CLP及跨语言自洽提示CLSP，通过跨语言对齐与任务特定求解生成推理路径，在多个基准上达到最先进性能。

摘要：

思维链（Chain-of-thought, CoT）能够引导模型显式地生成推理路径，从而提升推理准确性并吸引了越来越多的关注。具体而言，零样本CoT通过简单地用提示词“Let's think step by step!”指示LLM，在广泛的推理任务中取得了显著改进。尽管零样本CoT取得了成功，但现有的零样本提示技术仍局限于单一语言，使其难以泛化到其他语言并阻碍了全球化发展。在这项工作中，我们提出了跨语言提示（cross-lingual prompting, CLP），旨在改进跨语言的零样本CoT推理。具体而言，CLP包含两个主要组件：（1）跨语言对齐提示和（2）任务特定求解器提示。跨语言对齐提示负责对齐不同语言的表示，而任务特定求解器提示则用于为推理任务生成最终的思维链和结果。此外，我们进一步引入了跨语言自洽提示（cross-lingual self-consistent prompting, CLSP），以集成跨语言的不同推理路径。我们在多个基准上的实验评估表明，CLP和CLSP显著优于现有的提示方法，并实现了最先进的性能。我们希望这项工作能激发跨语言CoT领域的进一步突破。

英文摘要：

Chain-of-thought (CoT) is capable of eliciting models to explicitly generate reasoning paths, thus promoting reasoning accuracy and attracting increasing attention. Specifically, zero-shot CoT achieves remarkable improvements in a wide range of reasoning tasks by simply instructing the LLM with the prompt "Let's think step by step!". Despite the success of zero-shot CoT, the existing zero-shot prompting techniques remain limited to a single language, making it challenging to generalize to other languages and hindering global development. In this work, we introduce cross-lingual prompting (CLP), aiming to improve zero-shot CoT reasoning across languages. Specifically, CLP consists of two main components: (1) cross-lingual alignment prompting and (2) task-specific solver prompting. The cross-lingual alignment prompting is responsible for aligning representations across different languages, whereas the task-specific solver prompting is used to generate the final chain of thoughts and results for the reasoning task. In addition, we further introduce cross-lingual self-consistent prompting (CLSP) to ensemble different reasoning paths across languages. Our experimental evaluations on several benchmarks demonstrate that CLP and CLSP significantly outperform the existing prompting methods and achieve state-of-the-art performance. We hope this work will inspire further breakthroughs in cross-lingual CoT.

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。