Awesome RL with Human Feedback / 2020 and before / arXiv

Learning to summarize from human feedback

作者：Nisan Stiennon, Long Ouyang, Jeff Wu, Daniel M. Ziegler, Ryan Lowe, Chelsea Voss, Alec Radford, Dario Amodei, Paul Christiano · 来源：arXiv · 发布日期：2020

奖励建模偏好学习人类反馈设计长文本/对话
新标签打开 AlphaXiv新标签打开 Code新标签打开 Dataset
Learning to summarize from human feedback figure
AlphaXiv 中文概览（可滚动查看）