Large language models (LLMs) are artificial intelligence (AI) platforms capable of analyzing and mimicking natural language processing. Leveraging deep learning, LLM capabilities have been advanced significantly, giving rise to generative chatbots such as Generative Pre-trained Transformer (GPT). GPT-1 was initially released by OpenAI in 2018. ChatGPT's release in 2022 marked a global record of speed in technology uptake, attracting more than 100 million users in two months. Consequently, the utility of LLMs in fields including engineering, healthcare, and education has been explored. The potential of LLM-based chatbots in higher education has sparked significant interest and ignited debates. LLMs can offer personalized learning experiences and advance asynchronized learning, potentially revolutionizing higher education, but can also undermine academic integrity. Although concerns regarding AI-generated output accuracy, the spread of misinformation, propagation of biases, and other legal and ethical issues have not been fully addressed yet, several strategies have been implemented to mitigate these limitations. Here, the development of LLMs, properties of LLM-based chatbots, and potential applications of LLM-based chatbots in higher education are discussed. Current challenges and concerns associated with AI-based learning platforms are outlined. The potentials of LLM-based chatbot use in the context of learning experiences in higher education settings are explored.