AINeutralarXiv – CS AI · 7h ago6/10
🧠
Calibrated Preference Learning: The Case of Label Ranking
Researchers formalize calibration concepts for probabilistic label ranking, revealing that popular models often fail to align predicted probabilities with actual outcome frequencies. The framework uncovers a gap between sub-ranking and top-k calibration metrics, with implications for RLHF reward models used in AI systems.