Innovation and Optimization Approaches of College English Vocabulary Teaching Enabled by Generative Artificial Intelligence

Abstract

Drawing on the Input and Output Hypotheses, this study aims to address the persistent challenges of surface-level processing, homogenization and decontextualization in traditional college English vocabulary teaching and enhance students' pragmatic competence. To this end, by integrating the features of generative artificial intelligence (Gen AI), it explores the synergies between Gen AI and college English vocabulary teaching. To overcome the limitations of current vocabulary teaching, the study leverages Gen AI for dynamic context generation, personalized adaptation and real-time error correction. It then constructs innovative teaching models to facilitate deep vocabulary acquisition and establishes an optimization system for stage-based teaching processes, human-AI collaborative teaching and dynamic vocabulary assessment, thereby forming a new paradigm that unifies teaching, learning and assessment. The findings provide guidance for the digital and intelligent transformation of college English vocabulary teaching and offer empirical evidence for further research on the integration of Gen AI into foreign language instruction.