Awesome RL with Human Feedback / 2024 / arXiv

Direct Large Language Model Alignment Through Self-Rewarding Contrastive Prompt Distillation

作者：Aiwei Liu, Haoping Bai, Zhiyun Lu, Xiang Kong, Simon Wang, Jiulong Shan, Meng Cao, Lijie Wen · 单位：Tsinghua University · 来源：arXiv · 发布日期：2024

奖励建模偏好学习对齐目标设计策略优化无奖励对齐
新标签打开 AlphaXiv新标签打开 Code
Direct Large Language Model Alignment Through Self-Rewarding Contrastive Prompt Distillation figure
AlphaXiv 中文概览（可滚动查看）