Awesome RL with Human Feedback / 2022 / arXiv

Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

作者：Deep Ganguli, Liane Lovitt, Jackson Kernion, et al · 来源：arXiv · 发布日期：2022

安全对齐样本效率数据筛选
新标签打开 AlphaXiv新标签打开 Code
Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned figure
AlphaXiv 中文概览（可滚动查看）