SOURCE-LINKED INTELLIGENCE

CARE: Contrastive Anchor-based Rubric Evolution for Large Language Model Post-Training

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

Rubric-based reinforcement learning decomposes open-ended instructions into prompt-specific, flexible rubrics, making it better suited than reinforcement learning with verifiable rewards for post-training LLMs on open-ended tasks. However, static rubrics are inevitably hacked as the policy evolves, and existing dynamic approaches introduce new problems: undirected rubric extraction, unreliable hack detection, and unbounded rubric proliferation. We propose $\textbf{CARE}$ ($\textbf{C}$ontrastive $\textbf{A}$nchor-based $\textbf{R}$ubric $\textbf{E}$volution), which grounds every rubric evolutio

Read original source ↗ Open in workspace

recordType

paper

region

Global