reinforcement learning on Sadman Kabir Soumik

reinforcement learning on Sadman Kabir Soumik https://soumik.blog/tags/reinforcement-learning/ Recent content in reinforcement learning on Sadman Kabir Soumik Hugo -- gohugo.io en Copyright © 2022, Sadman Kabir Soumik Sun, 14 Dec 2025 18:00:00 +0000 How LLM Post Training Works: SFT, Preference Training, Reinforcement Learning, and Distillation https://soumik.blog/artificial-intelligence/how-llm-post-training-works/ Sun, 14 Dec 2025 18:00:00 +0000 https://soumik.blog/artificial-intelligence/how-llm-post-training-works/ Training a large language model usually happens in more than one stage. The first stage is pretraining. This is where the model learns language, facts, patterns, coding concepts, reasoning patterns, and many other things from a very large amount of data. But a pretrained model is not automatically a good assistant. It might know a lot, but it may still struggle to follow instructions, answer in the right format, understand human preferences, or behave the way we want.