#Uncertainty Quantification

2 articles with this tag

First-Token Confidence as AI Hallucination Baseline
AI Research

First-Token Confidence as AI Hallucination Baseline

First-token confidence (phi_first) emerges as a highly efficient and effective method for AI hallucination detection, outperforming complex multi-sample approaches.

about 1 month ago
Bayesian Uncertainty for Foundation Models
AI Research

Bayesian Uncertainty for Foundation Models

Variational Mixture-of-Experts Routing (VMoER) offers a scalable Bayesian approach to uncertainty quantification in foundation models, achieving significant improvements with minimal computational overhead.

3 months ago