C4. Inverting it: your language model is a reward model

C4. Inverting it: your language model is a reward model Lesson 13 of 20 in "Direct Preference Optimization, from scratch". Paper: Rafailov et al., "Direct Preference Optimization: Your Language Model is Secretly a Reward Model" (NeurIPS 2023), https://arxiv.org/abs/2305.18290