Awesome RL with Human Feedback / 2023 / arXiv

RRHF: Rank Responses to Align Language Models with Human Feedback without tears

作者：Zheng Yuan, Hongyi Yuan, Chuanqi Tan, Wei Wang, Songfang Huang, Fei Huang · 单位：Alibaba DAMO Academy, Tsinghua University · 来源：arXiv · 发布日期：2023

偏好学习对齐目标设计策略优化人类反馈设计
新标签打开 AlphaXiv新标签打开 Code
RRHF: Rank Responses to Align Language Models with Human Feedback without tears figure
AlphaXiv 中文概览（可滚动查看）