The design of prompts driven by Chain of Thought in multicultural teaching

Generative large language models (LLMs) show promise in multicultural teaching, but existing methods rely heavily on labeled data and resources, struggling to capture cultural nuances and generalize across various teaching contexts. To address the above issues, the paper introduces an innovative method called Multicultural Prompt Learning (MPL), which applies Chain of Thought (CoT) to prompt design. By gradually refining prompts, multicultural elements are integrated step by step, enabling AI to better understand and handle cultural nuances. This approach produces richer, more accurate, and diverse outputs, specifically aimed at enhancing students’ understanding of different cultures in multicultural teaching contexts. The experiment used a questionnaire, including image quality evaluation and a blind content comprehension, to compare Chain of Thought and traditional prompts. Results show Chain of Thought prompts outperform traditional methods in all dimensions, offering greater practical and educational value.