Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubrics
Paper • 2609.38847 • Published • 61
Yuni Wijaya
mangoyuni
AI & ML interests
recommendation systems, bioinformatics, robotics, model evaluation
Recent Activity
upvoted a paper about 21 hours ago
Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubrics updated a model 2 days ago
mangoyuni/robotics-vision-language-notes published a model 2 days ago
mangoyuni/robotics-vision-language-notesOrganizations
None yet
upvoted a paper about 21 hours ago
updated a
model 2 days ago
published a
model 2 days ago
updated a
dataset 2 days ago
published a
dataset 2 days ago
liked a
model 2 days ago
