Research on the Application Path of Large Language Models in Situational Teaching of "Morality and Law" in Junior High School

Abstract

In the context of curriculum reform oriented towards core competencies, teachers are required to innovate their teaching methods and integrate abstract theoretical knowledge with vivid scenarios. Situational teaching has become a key method for enhancing the effectiveness of moral and legal education in junior high school. However, there are still common issues in current teaching practice, such as insufficient authenticity of scenarios, uneven student participation, and singular teaching evaluation. Large Language Models (LLMs), represented by generative artificial intelligence, provide a new technical solution to address these challenges with their powerful capabilities in content generation, natural interaction, and data analysis. Based on teaching practice, this paper systematically analyzes the main issues facing situational teaching in junior high school moral and legal education. It deeply explains the mechanism by which LLMs empower teaching through enriching situational materials, supporting human-computer dialogue, and enabling process-oriented data collection. Centered around the three stages of teaching design, implementation, and evaluation, it constructs an application path of "intelligent situational construction - human-computer collaborative interpretation - accompanying feedback optimization" to enhance the timeliness of junior high school moral and legal education.