Available Guardrails: Certifying Selective Prediction across ML Systems
An Interpretable Memory Decision Controller for LLM Agents Based on Three-Signal Complementarity: Decoupling Confidence and Consistency
Abstention and Noise Filtering: Two Missing Primitives of Softmax Attention
When Should LLMs Abstain? Chain-of-Self-Questioning for Selective Risk Control
1
Competence-Gated Pooling of Language Models and Priors for Event Forecasting
1
Recognition-Refusal Misalignment in LLMs: Why Models Answer Structurally Unanswerable Questions
