AIBullisharXiv – CS AI · 15h ago6/10
🧠
LEC: Linear Expectation Constraints for Selection-Conditioned Risk Control in Selective Prediction and Routing Systems
Researchers propose LEC (Linear Expectation Constraints), a framework for controlling prediction errors in foundation models by setting user-specified risk thresholds. The method enables selective prediction systems and multi-model routing architectures to maintain statistical guarantees on error rates while maximizing the number of accepted predictions, with applications spanning QA and vision tasks.