NLP@Stanford ; RL from Human Feedback AND RL from Human Feedback
Common descendants
3 Documents
Archit Sharma sur Twitter : "Direct Preference Optimization (DPO) allows you to fine-tune LMs directly from preferences via a simple classification loss, no RL required"
Tags:
2023-05-31 About
Eric sur Twitter : "...Introducing Direct Preference Optimization (DPO), a simple classification loss provably equivalent to RLHF"
Tags:
2023-05-31 About
Prompting, Instruction Finetuning, and RLHF (CS224N)
Tags:
2023-02-16 About