RUBRIC-ARROW: Alternating Pointwise Rubric Reward Modeling for LLM Post-training in Non-verifiable Domains
Paper • 2605.29156 • Published • 6
Yi-Chung Chen
andrew0111
AI & ML interests
None yet
Recent Activity
upvoted a paper about 14 hours ago
RUBRIC-ARROW: Alternating Pointwise Rubric Reward Modeling for LLM Post-training in Non-verifiable DomainsOrganizations
None yet
upvoted a paper about 14 hours ago