NLP@Stanford AND Human in the loop
Descendants partagés
4 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 A propos
Eric sur Twitter : "...Introducing Direct Preference Optimization (DPO), a simple classification loss provably equivalent to RLHF"
Tags:
2023-05-31 A propos
Prompting, Instruction Finetuning, and RLHF (CS224N)
Tags:
2023-02-16 A propos
Stanford NLP Group sur Twitter : "...how to use AI systems to augment the work of humans in interactive systems "
Tags:
2022-03-05 A propos