有害性低減

書いてみる

関連タグ

#MCTS (9)
#PPO (11)
#RL (271)
#SL (686)
#スコア (1,185)
#タスク (8,388)

Constitutional AI: Harmlessness from AI Feedback

Ikemen Mas Kot
8か月前

Don't throw away your value model! Generating more preferable text with Value-Guided Monte-Carlo Tree Search decoding

Ikemen Mas Kot
9か月前