Uncertainty quantification (UQ) methods play a pivotal role in reducing the impact of
uncertainties during both optimization and decision making processes. They have been …

We introduce a method to measure uncertainty in large language models. For tasks like
question answering, it is essential to know when we can trust the natural language outputs …

The Bayesian paradigm has the potential to solve core issues of deep neural networks such
as poor calibration and data inefficiency. Alas, scaling Bayesian inference to large weight …

Abstract While Bayesian neural networks (BNNs) hold the promise of being flexible, well-
calibrated statistical models, inference often requires approximations whose consequences …

In this paper, we study the problem of uncertainty estimation and calibration for LLMs. We
begin by formulating the uncertainty estimation problem, a relevant yet underexplored area …

Abstract We propose Radial Bayesian Neural Networks (BNNs): a variational approximate
posterior for BNNs which scales well to large models. Unlike scalable Bayesian deep …

Stochastic variational inference for Bayesian deep neural network (DNN) requires specifying
priors and approximate posterior distributions over neural network weights. Specifying …

Bayesian neural networks (BNN) are powerful parametric models for nonlinear regression
with uncertainty quantification. However, the approximate inference techniques for weight …

The COVID-19 pandemic has highlighted the global need for reliable models of disease
spread. We propose an AI-augmented forecast modeling framework that provides daily …

We detect out-of-training-distribution sentences in Neural Machine Translation using the
Bayesian Deep Learning equivalent of Transformer models. For this we develop a new …