RUBRIC-ARROW: Alternating Pointwise Rubric Reward Modeling for LLM Post-training in Non-verifiable Domains
Paper • 2605.29156 • Published • 14
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
RUBRIC-ARROW: Alternating Pointwise Rubric Reward Modeling for LLM Post-training in Non-verifiable Domains
Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-Training
haoyuw
authored a
paper 14 days ago
Dazzlinglights
updated a
model 17 days ago
Add link to paper and task category metadata
#2 opened 17 days ago
by 
nielsr
Add metadata and link to paper
#1 opened 17 days ago
by nielsr
Add metadata and link to paper
#1 opened 17 days ago
by nielsr
lliutianc
updated 2
models 17 days ago
lliutianc
authored 2
papers 17 days ago
lliutianc
submitted a
paper to Daily Papers 17 days ago
Dazzlinglights
updated a
dataset 19 days ago
Dazzlinglights
published a
dataset 19 days ago
Dazzlinglights
updated a
collection 19 days ago
Dazzlinglights
updated a
model 19 days ago
Dazzlinglights
published 2
models 19 days ago
lliutianc
updated 3
models 2 months ago