Learn how to improve the performance of large language models (LLMs) using human-generated data. This specialization provides an introduction to the post-training pipeline, including Reinforcement Learning from Human Feedback (RLHF) and other alignment techniques. You’ll gain a practical understanding of the LLM training lifecycle, and develop the skills to generate high-quality data that addresses key challenges such as hallucinations and misalignment. The course emphasizes real-world applications in data analysis, data science, code generation, and implicit code execution (ICE).