Texonom
Texonom
/
Engineering
Engineering
/Data Engineering/Artificial Intelligence/Machine Learning/Reinforcement Learning/Reinforcement Learning Method/Reward model/Verifiable Reward/
Format reward
Search

Format reward

Creator
Creator
Seonglae ChoSeonglae Cho
Created
Created
2025 Apr 16 13:6
Editor
Editor
Seonglae ChoSeonglae Cho
Edited
Edited
2026 Mar 22 0:44
Refs
Refs
 
 
 
 
 
 
reduce format reward bias
AI Reward Hacking
by SAE feature steeringa
arxiv.org
https://arxiv.org/pdf/2603.12795
 

Recommendations

Texonom
Texonom
/
Engineering
Engineering
/Data Engineering/Artificial Intelligence/Machine Learning/Reinforcement Learning/Reinforcement Learning Method/Reward model/Verifiable Reward/
Format reward
Copyright Seonglae Cho