AIBullisharXiv – CS AI · 10h ago7/10
🧠
Auto-Rubric as Reward: From Implicit Preferences to Explicit Multimodal Generative Criteria
Researchers introduce Auto-Rubric as Reward (ARR), a framework that replaces opaque scalar reward signals in multimodal AI alignment with explicit, structured criteria-based evaluation. By externalizing a model's implicit preferences into interpretable rubrics before comparison, ARR reduces evaluation bias and enables more reliable human-preference alignment in generative models.