Steerable Cultural Preference Optimization of Reward Models Paper • 2606.18606 • Published Jun 17 • 3
SCPO country reward models Collection Country-specific SCPO reward models. Paper: arxiv.org/abs/2606.18606. • 8 items • Updated 27 days ago • 3
MulticulturalAlignment/scpo-reward-model-south-africa Text Classification • 0.2B • Updated 27 days ago • 31 • 1
MulticulturalAlignment/scpo-reward-model-new-zealand Text Classification • 0.2B • Updated 27 days ago • 25 • 1
MulticulturalAlignment/scpo-reward-model-mexico Text Classification • 0.2B • Updated 27 days ago • 22 • 1
MulticulturalAlignment/scpo-reward-model-israel Text Classification • 0.2B • Updated 27 days ago • 24 • 1
MulticulturalAlignment/scpo-reward-model-chile Text Classification • 0.2B • Updated 27 days ago • 29 • 1
MulticulturalAlignment/scpo-reward-model-canada Text Classification • 0.2B • Updated 27 days ago • 27 • 1
MulticulturalAlignment/scpo-reward-model-australia Text Classification • 0.2B • Updated 27 days ago • 20 • 1
SCPO country reward models Collection Country-specific SCPO reward models. Paper: arxiv.org/abs/2606.18606. • 8 items • Updated 27 days ago • 3
MulticulturalAlignment/scpo-reward-model-south-africa Text Classification • 0.2B • Updated 27 days ago • 31 • 1
MulticulturalAlignment/scpo-reward-model-new-zealand Text Classification • 0.2B • Updated 27 days ago • 25 • 1
MulticulturalAlignment/scpo-reward-model-mexico Text Classification • 0.2B • Updated 27 days ago • 22 • 1
MulticulturalAlignment/scpo-reward-model-israel Text Classification • 0.2B • Updated 27 days ago • 24 • 1