Cross-lingual Prompting: Improving Zero-shot Chain-of-Thought Reasoning across Languages
This work addresses the challenge of generalizing reasoning techniques across languages, which is important for global AI development but is incremental as it builds on existing zero-shot CoT methods.
The paper tackles the problem of zero-shot chain-of-thought reasoning being limited to single languages by introducing cross-lingual prompting (CLP) and cross-lingual self-consistent prompting (CLSP), which significantly outperform existing methods and achieve state-of-the-art performance on several benchmarks.
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.