230602 Fine-Grained Human Feedback Gives Better Rewards for Language Model Training.md

https://arxiv.org/abs/2306.01693

Fine-Grained Human Feedback Gives Better Rewards for Language Model Training (Zeqiu Wu, Yushi Hu, Weijia Shi, Nouha Dziri, Alane Suhr, Prithviraj Ammanabrolu, Noah A. Smith, Mari Ostendorf, Hannaneh Hajishirzi)