Trustworthy Calibration or Vulnerability? Unveiling the Over-Calibration Paradox and Attack Surface in Rashomon Sets
cs.LG
Submitted: 2026-03-12
Updated: 2026-11-16
Terminology
Sources
- Towards A Rigorous Science of Interpretable Machine Learning
- Improving Perturbation-based Explanations by Understanding the Role of Uncertainty Calibration
- Using predictive multiplicity to measure individual performance within the AI Act
- Calibration Meets Reality: Making Machine Learning Predictions Trustworthy
- An Experimental Study on the Rashomon Effect of Balancing Methods in Imbalanced Classification
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis