Applying Large Language Models in Education

As a significant breakthrough in the realm of generative artificial intelligence, large language models (LLMs) are increasingly permeating educational landscapes and revolutionizing teaching and learning. LLMs possess robust semantic comprehension, text generation and image generation capabilities that surpass traditional natural language processing methods. The application based on LLMs not only provides students with abundant learning resources but also offers diverse learning scaffolds to guide them in problem-solving. Additionally, LLMs can be utilized for automated teaching diagnosis, mitigating teachers' workload while enabling them to grasp learning situations efficiently, adjust teaching strategies, and devise more effective teaching evaluation methods.

Currently, a wide range of LLMs-based applications is emerging, including language translation, oral training, essay correction, programming tutoring, automatic problem-solving, automatic problem-solving, image generation. Nevertheless, the technology of LLMs has not yet matured, and some limitations and errors may occur, which adds barriers to the ground application of LLMs in education. Meanwhile, students' over-reliance on such tools may also lead to negative impacts. In addition, there is still a lack of evidence on how to properly and effectively utilize various types of assistants based on LLMs, and whether such tools can truly enhance learning. Therefore, further empirical research is urgently needed to address these issues.

Topics of this workshop

The workshop aims to provide a platform for academic exchanges and discussions, where participants can share relevant research results, teaching practices, and innovative cases, and jointly explore the application of LLMs (including multimodal LLMs) in teaching practice and research. By exchanging experiences and ideas, the workshop aims to promote in-depth research and sharing of practical experiences in this field among academics. This workshop mainly focuses on the following topics:

• Design of prompts for teaching and learning scenarios;
• Analysis of the interaction process between humans and LLMs;
• Intelligent agents based on LLMs;
• Application of LLMs in teaching design and teaching resource development;
• Application of LLMs in personalized learning;
• Application of LLMs in automatic evaluation and feedback generation;
• Application of LLMs in educational data analysis and decision support;
• Cooperative learning based on LLMs;
• Game-based learning and educational Games based on LLMs.