AI RESEARCH
CDRRM: Contrast-Driven Rubric Generation for Reliable and Interpretable Reward Modeling
arXiv CS.LG
•
ArXi:2603.08035v1 Announce Type: cross Reward modeling is essential for aligning Large Language Models(LLMs) with human preferences, yet conventional reward models suffer from poor interpretability and heavy reliance on costly expert annotations. While recent rubric-based approaches enhance evaluation transparency, they lack systematic quality control, yielding noisy and redundant criteria, failing to mitigate persistent biases (e.g., verbosity, position) in LLM evaluators, and creating a scalability-reliability trade-off.