calibration
The process of adjusting the output of a probabilistic model to ensure that its predicted probabilities reflect true likelihoods or frequencies, which is crucial for decision-making.
- Aligning Evaluation with Clinical Priorities: Calibration, Label Shift, and Error Costs
- Are Large Reasoning Models Good Translation Evaluators? Analysis and Performance Boost
- Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)
- Belief-Calibrated Multi-Agent Consensus Seeking for Complex NLP Tasks
- Bridging Human and LLM Judgments: Understanding and Narrowing the Gap
- Causal Explanation-Guided Learning for Organ Allocation
- ConfTuner: Training Large Language Models to Express Their Confidence Verbally
- Consistency Conditions for Differentiable Surrogate Losses
- Diffusion-Guided Graph Data Augmentation
- Geometric Logit Decoupling for Energy-Based Graph Out-of-distribution Detection
- Kernel-based Equalized Odds: A Quantification of Accuracy-Fairness Trade-off in Fair Representation Learning
- MagCache: Fast Video Generation with Magnitude-Aware Cache
- On Group Sufficiency Under Label Bias
- Optimal and Provable Calibration in High-Dimensional Binary Classification: Angular Calibration and Platt Scaling
- Performative Risk Control: Calibrating Models for Reliable Deployment under Performativity
- Rectifying Soft-Label Entangled Bias in Long-Tailed Dataset Distillation
- Simultaneous Swap Regret Minimization via KL-Calibration
- The Illusion of Progress? A Critical Look at Test-Time Adaptation for Vision-Language Models
- Uncertainty Quantification for Deep Regression using Contextualised Normalizing Flows
- Understanding and Rectifying Safety Perception Distortion in VLMs