Probing Preference Representations: A Multi-Dimensional Evaluation and Analysis Method for Reward Models
wangchenglong
wangclnlp
·
AI & ML interests
None yet
Recent Activity
updated
a collection
2 days ago
Probing-RM
upvoted
a
paper
2 months ago
Parallel-R1: Towards Parallel Thinking via Reinforcement Learning
upvoted
a
paper
2 months ago
GRAM-R^2: Self-Training Generative Foundation Reward Models for Reward
Reasoning
Organizations
Self-Training Generative Foundation Reward Models for Reward Reasoning
-
GRAM-R^2: Self-Training Generative Foundation Reward Models for Reward Reasoning
Paper • 2509.02492 • Published • 1 -
wangclnlp/GRAM-RR-LLaMA-3.1-8B-RewardModel
Text Generation • 8B • Updated • 6 -
wangclnlp/GRAM-RR-LLaMA-3.2-3B-RewardModel
Text Generation • 3B • Updated • 13 -
wangclnlp/GRAM-RR-TrainingData
Updated • 92
Probing Preference Representations: A Multi-Dimensional Evaluation and Analysis Method for Reward Models
Self-Training Generative Foundation Reward Models for Reward Reasoning
-
GRAM-R^2: Self-Training Generative Foundation Reward Models for Reward Reasoning
Paper • 2509.02492 • Published • 1 -
wangclnlp/GRAM-RR-LLaMA-3.1-8B-RewardModel
Text Generation • 8B • Updated • 6 -
wangclnlp/GRAM-RR-LLaMA-3.2-3B-RewardModel
Text Generation • 3B • Updated • 13 -
wangclnlp/GRAM-RR-TrainingData
Updated • 92