Awesome RL with Human Feedback / 2025 / arXiv

Exploring Data Scaling Trends and Effects in Reinforcement Learning from Human Feedback

作者：Wei Shen, Guanlin Liu, Zheng Wu, Ruofei Zhu, Qingping Yang, Chao Xin, Yu Yue, Lin Yan · 单位：ByteDance Seed · 来源：arXiv · 发布日期：2025

奖励黑客/过优化奖励建模偏好学习样本效率数据筛选
新标签打开 AlphaXiv
Exploring Data Scaling Trends and Effects in Reinforcement Learning from Human Feedback figure
AlphaXiv 中文概览（可滚动查看）