CS 543 Large Language Models

Explores the architecture, underlying principles, and applications of large language models (LLMs), including transformers, tokenization, attention mechanisms, embeddings, fine-tuning, and safety. Students analyze model behavior, evaluate performance, and build LLM-powered systems while examining societal and ethical implications. Hands-on projects emphasize practical implementation and critical understanding of limitations. Expected preparation: programming skills and prior exposure to basic linear algebra and probability.