EMNLP2023

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

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

26 citations

Abstract

Chain-of-thought (CoT) is capable of eliciting models to explicitly generate reasoning paths, thus promoting reasoning accuracy and attracting increasing attention. Specifically, zeroshot 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) taskspecific 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. Answer: 48. After understanding, you should act as an expert in arithmetic reasoning in German… Verstanden! Hier ist die Lösung für die gegebene Aufgabe: 1. Da Jiesha 20 Jahre alt ist, ist Qioung 20-5... 2. Da Mary zwei Jahre jünger als Qioung ist... Antwort: 48. Sorry, I am an AI language model and I can only communicate in English. May I assist you with anything else? Let's understand the task in German step-by-step! German Prompting Please act as an expert in multi-lingual understanding in Chinese. Request:玛丽比琼小两岁,琼比杰莎大五岁。如果杰莎 20 岁,这 三个女孩的年龄总和是多少? Let's understand the task in English step-by-step! After understanding, you should act as an expert in arithmetic reasoning in English. Let's resolve the task you understand above step-by-step! Finally, you should format your answer as 'Answer: [num]'. Sure! Let's solve the task step-by-step: 1. According to the first sentence, Mary is two years younger than Joan. Let's suppose Joan's age is J, then Mary's age is J -2. 2. According to the second sentence, Joan is five years older than Jessie. If Jessie's age is x, then Joan's age is x + 5... Answer: 68. 1. "玛丽比琼小两岁" means "Mary is two years younger than Joan." 2. "琼比杰莎大五岁" means "Joan is five years older than Jessie. " 1. "玛丽比琼小两岁" means "Mary is two … 2. "琼比杰莎大五岁" means "Joan is five … 3. "如果杰莎 20 岁" means "If Jessie is 20… Let's understand the task in English step-by-step! English Prompting Answer: 68. Cross-lingual Alignment Prompting Task-specific Solver Prompting (a) Cross-lingual Prompting (CLP) Answer: 68. Answer: 68. Please act as an expert in multi-lingual understanding in Chinese.