R3: Robust Rubric-Agnostic Reward Models

arXiv:2505.13388v4 Announce Type: replace-cross Abstract: Reward models are essential for aligning language model outputs with human preferences, yet existing approaches often lack both controllability and interpretability. These models are typically optimized for narrow objectives, limiting their generalizability to broader downstream tasks. Moreover, their scalar outputs are difficult to interpret without contextual reasoning. To address these limitations, we introduce R3, a novel reward modeling framework that is rubric-agnostic, generalizable across evaluation dimensions, and provides interpretable, reasoned score assignments. R3 enables more transparent and flexible evaluation of language models, supporting robust alignment with diverse human values and use cases. Our models, data, and code are available as open source at https://github.com/rubricreward/r3.

Related

• Debiasing Reward Models via Causally Motivated Inference-Time Intervention
• In-Context Reward Adaptation for Robust Preference Modeling
• Factored Causal Representation Learning for Robust Reward Modeling in RLHF

Source: arXiv cs.AI | 2026-09-16