Large Language Models

3 units

Large Language Models (LLMs) have revolutionized the field of artificial intelligence, offering unprecedented capabilities in understanding and generating human-like text. This is a research-oriented course that explores the capabilities and challenges of LLMs. Students will gain a comprehensive understanding of the underlying mechanisms that power these models, as well as reading frontier papers and working on projects to gain hands-on experience. Topics to be covered include LLM training, LLM capabilities, safety, ethical considerations, approaches to augment LLMs, efficiency of modeling and training LLMs, etc.