Advanced Topics in Computer Science: Deep Dive into Large Language Models

Large language models (LLMs) have revolutionized natural language processing by enabling machines to generate, understand, and interact with human language in more sophisticated ways than ever before. This course aims to provide a rigorous survey of current LLM research, including model architecture, data preparation, pre-training, post-training/alignment, and model deployment. The course focuses on conceptual understanding and research rather than engineering, and it is highly interactive. Students are expected to read research papers regularly, participate in discussion, maintain a journal, and complete a major project at the end.