R3: Robust Rubric-Agnostic Reward Models
This addresses the problem of aligning language models with diverse human values for researchers and practitioners, though it appears incremental as it builds on existing reward modeling approaches.
The paper tackles the lack of controllability and interpretability in reward models for aligning language models with human preferences by introducing a rubric-agnostic framework that provides interpretable, reasoned score assignments, enabling more transparent and flexible evaluation.
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 $\shortmethodname$, a novel reward modeling framework that is rubric-agnostic, generalizable across evaluation dimensions, and provides interpretable, reasoned score assignments. $\shortmethodname$ 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.