Abstention as an Action Can Kill Both the Reward Gradient and the KL Anchor: Collapse Law and Repair for Error-Penalized Reinforcement Learning

英文标题：Abstention as an Action Can Kill Both the Reward Gradient and the KL Anchor: Collapse Law and Repair for Error-Penalized Reinforcement Learning

arXiv:2608.00301v1 Announce Type: new Abstract: Error-penalized scoring rules ($+1$ for a correct answer, $-\lambda$ for a wrong one, $0$ for abstaining) are increasingly prescribed against hallucination: a rational agent facing such a rule answers exactly when its correctness probability exceeds C

2.6 KB 2.1 KB 612 B 380 B 9.1 KB 32.7 KB 22.8 KB 24.2 KB 34.7 KB