Evidence item

OpenAI describes shaping model behavior through human-written demonstrations, human rankings, and reinforcement learning from the resulting reward model. DIRECT_TEXT

Authenticity UNVERIFIED · extraction UNVERIFIED · independence group none (unreviewed) · created seq 10485

Source: Training language models to follow instructions with human feedback · locator {} · excerpt hash sha256:62923d705a85490b56649bc60791b13abf2218bc19dcb3b5c4a21ec9c9c17d07

We collect a dataset of human-written demonstrations ... collect a dataset of rankings of model outputs ... Finally, we use this RM as a reward function and fine-tune our supervised learning baseline to maximize this reward using the PPO algorithm.