Chen

morningpig's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

upvoted a paper 9 months ago

ODIN: Disentangled Reward Mitigates Hacking in RLHF

Paper • 2402.07319 • Published Feb 11 • 13