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

2023/10/23 by Libo Qin, Qiguang Chen, Qin, Libo +7 · 25 citations
Computer Science · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Machine Learning in Healthcare

paper · pdf · doi:10.48550/arxiv.2310.14799

openalex publication_date 2023/10/23 · openalex created_date 2023/10/25 · openalex updated_date 2026/07/28

Abstract

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.

Cited by

• Beg to Differ: Understanding Reasoning-Answer Misalignment Across Languages
• Retrieval-augmented Prompt Learning for Pre-trained Foundation Models
• Beware of Reasoning Overconfidence: Pitfalls in the Reasoning Process for Multi-solution Tasks
• MPR-GUI: Benchmarking and Enhancing Multilingual Perception and Reasoning in GUI Agents
• Unlocking Multilingual Reasoning Capability of LLMs and LVLMs through Representation Engineering
• Beyond MCQ: An Open-Ended Arabic Cultural QA Benchmark with Dialect Variants
• Cross-Lingual Stability and Bias in Instruction-Tuned Language Models for Humanitarian NLP
• Rethinking Cross-lingual Gaps from a Statistical Viewpoint
• Unlocking LLM Safeguards for Low-Resource Languages via Reasoning and Alignment with Minimal Training Data
• AutoPR: Let's Automate Your Academic Promotion!
• Beyond Surface Reasoning: Unveiling the True Long Chain-of-Thought Capacity of Diffusion Large Language Models
• A Comprehensive Evaluation of Multilingual Chain-of-Thought Reasoning: Performance, Consistency, and Faithfulness Across Languages
• SoT: Structured-of-Thought Prompting Guides Multilingual Reasoning in Large Language Models
• Learning to Ponder: Adaptive Reasoning in Latent Space
• Beyond English-Centric Training: How Reinforcement Learning Improves Cross-Lingual Reasoning in LLMs
• MERLIN: Multi-Stage Curriculum Alignment for Multilingual Encoder-LLM Integration in Cross-Lingual Reasoning
• Language-Specific Layer Matters: Efficient Multilingual Enhancement for Large Vision-Language Models
• Long Chain-of-Thought Reasoning Across Languages
• Aware First, Think Less: Dynamic Boundary Self-Awareness Drives Extreme Reasoning Efficiency in Large Language Models
• Utilizing Multilingual Encoders to Improve Large Language Models for Low-Resource Languages
• A Survey on Training-free Alignment of Large Language Models
• What Factors Affect LLMs and RLLMs in Financial Question Answering?
• EfficientXLang: Towards Improving Token Efficiency Through Cross-Lingual Reasoning
• Format-Adapter: Improving Reasoning Capability of LLMs by Adapting Suitable Format
• Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study

Related

• AutoCAP: Towards Automatic Cross-lingual Alignment Planning for Zero-shot Chain-of-Thought
• Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting
• xCoT: Cross-lingual Instruction Tuning for Cross-lingual Chain-of-Thought Reasoning
• A Comprehensive Evaluation of Multilingual Chain-of-Thought Reasoning: Performance, Consistency, and Faithfulness Across Languages
• Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models