Awesome RL with Human Feedback / 2022 / arXiv

Discovering Language Model Behaviors with Model-Written Evaluations

作者：Ethan Perez, Sam Ringer, Kamilė Lukošiūtė, Karina Nguyen, Edwin Chen, et al · 单位：Machine Intelligence Research Institute · 来源：arXiv · 发布日期：2022

评测/基准偏好学习
新标签打开 AlphaXiv新标签打开 Code新标签打开 Dataset
Discovering Language Model Behaviors with Model-Written Evaluations figure
AlphaXiv 中文概览（可滚动查看）