LLMs Aligned! But to What End?

Editor’s note: Sinan Ozdemir is a speaker for ODSC East this April 23–25. Be sure to check out his talk, “Aligning Open-source LLMs Using Reinforcement Learning from Feedback,” there!

Introduction — Re-aligning Our Expectations of AI

Reinforcement Learning (RL) has become one of the primary engines powering AI alignment, the process of fine-tuning an AI model (usually LLMs) to behave according to a certain set of standards and styles. Reinforcement learning provides the unique ability to instill …

artificial intelligence data science language model llm open source