Learning to summarize with human feedback
核心要点速览
We’ve applied reinforcement learning from human feedback to train language models that are better at summarization.
查看完整报道与分享
完整图文、背景资料与讨论归原始发布平台 OpenAI News 所有。
We’ve applied reinforcement learning from human feedback to train language models that are better at summarization.
完整图文、背景资料与讨论归原始发布平台 OpenAI News 所有。