Peach and Plum Blossoms: A Large Model of International Chinese Education

Peach and Plum ": A Large Model of International Chinese Education

With the widespread attention of ChatGPT and the emergence of various Large Language Models, natural language processing tasks in the general field have achieved great success, attracting widespread attention in the international Chinese education field.

International Chinese educators have launched discussions on big models: can big models provide appropriate language expressions based on learners' levels, or provide detailed answers to learners' questions, thereby assisting or even serving as learning partners and language teachers to a certain extent? However, the effectiveness of large-scale models in the general domain is still limited in the vertical domain.

To address the aforementioned issues, we have fully launched the large model "Taoli" 1.0, which is suitable for the international Chinese education field. This model has undergone additional training on data from the international Chinese education field.

We have built an international Chinese education resource library based on over 500 international Chinese education textbooks and teaching aids, Chinese proficiency test questions, and Chinese learner dictionaries currently circulating in the international Chinese education field. We have set up various forms of instructions to fully utilize knowledge, constructed a high-quality international Chinese education question and answer dataset of 88000 items, and used the collected data to fine tune the model's instructions, enabling the model to acquire the ability to apply international Chinese education knowledge to specific scenarios.