Large Language Models Empowering Interpreting Teaching: A Research on User Satisfaction Survey and Functional Optimization Strategies

Abstract

To address the limitations of the "DeepSeek" large language model (LLM) in interpreting education, this study investigates user satisfaction and proposes optimization strategies by analyzing its application across pre-interpreting, while-interpreting, and post-interpreting phases. Targeting translation majors and learners, a questionnaire was designed to identify key factors influencing user satisfaction. Data analysis reveals critical insights, leading to tailored optimization strategies for each phase. The findings emphasize the necessity of integrating LLMs into interpreting pedagogy to enhance training efficiency, reduce cognitive load, and foster cross-disciplinary research capabilities.