Auditable Decision Models with Learned Abstention and Real-Time Steering 事件

Auditable Decision Models with Learned Abstention and Real-Time Steering arXiv:2605.27768v1 Announce Type: new Abstract: Production AI systems often operate with incomplete, conflicting, or insufficient evidence. Forced classifiers collapse such cases into action labels, while generative systems can produce outputs that are difficult to interpret as auditable execution decisions. We study operational decision control for AI systems, where uncertainty must be explicitly routable, policy-governed