Awesome RL with Human Feedback / 2023 / arXiv

Fine-Grained Human Feedback Gives Better Rewards for Language Model Training

作者：Zeqiu Wu, Yushi Hu, Weijia Shi, Nouha Dziri, Alane Suhr, Prithviraj Ammanabrolu, Noah A. Smith, Mari Ostendorf, Hannaneh Hajishirzi · 单位：University of Washington, Allen Institute for Artificial Intelligence, University of California, Berkeley, University of California, San Diego · 来源：arXiv · 发布日期：2023

奖励建模偏好学习信用分配/密集奖励人类反馈设计
新标签打开 AlphaXiv新标签打开 Code
Fine-Grained Human Feedback Gives Better Rewards for Language Model Training figure
AlphaXiv 中文概览（可滚动查看）