ODRPO: Ordinal Decompositions of Discrete Rewards for Robust Policy Optimization

arXiv:2605.12667v1 Announce Type: cross Abstract: The alignment of Large Language Models (LLMs) utilizes Reinforcement Learning from AI Feedback (RLAIF) for non-verifiable domains such as long-form question answering and open-ended instruction following. These domains often rely on LLM based...