This research aims to enhance language learning by modeling word meaning through Large Language Models (LLMs). Specifically, we aim to leverage LLMs for generating word sense definitions from in-context word examples. Our goal is to improve the tools available for language learners by advancing the computational modeling of lexical semantics. Drawing on recent advancements in Natural Language Processing, we will explore the capabilities of LLMs to generate clear and context-appropriate word sense definitions for various words. By providing coherent and consistent definitions, we aim to support learners in understanding different usages of words. This research has the potential to revolutionize language learning resources, particularly in tasks such as understanding word meanings and resolving ambiguities. Additionally, we believe that this work will have broader implications for NLP, contributing to more effective text generation and the development of new, more powerful language models.