Search Results for author:
Found 8 papers, 5 papers with code
Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations
A major barrier towards the practical deployment of large language models (LLMs) is their lack of reliability.
Quality-Aware Translation Models: Efficient Generation and Quality Estimation in a Single Model
Maximum-a-posteriori (MAP) decoding is the most widely used decoding strategy for neural machine translation (NMT) models.
Beyond In-Domain Scenarios: Robust Density-Aware Calibration
While existing post-hoc calibration methods achieve impressive results on in-domain test datasets, they are limited by their inability to yield reliable uncertainty estimates in domain-shift and out-of-domain (OOD) scenarios.
What Makes Graph Neural Networks Miscalibrated?
Furthermore, based on the insights from this study, we design a novel calibration method named Graph Attention Temperature Scaling (GATS), which is tailored for calibrating graph neural networks.
CHALLENGER: Training with Attribution Maps
Regularization is key in deep learning, especially when training complex models on relatively small datasets.
Parameterized Temperature Scaling for Boosting the Expressive Power in Post-Hoc Uncertainty Calibration
We address the problem of uncertainty calibration and introduce a novel calibration method, Parametrized Temperature Scaling (PTS).
Post-hoc Uncertainty Calibration for Domain Drift Scenarios
First, we show that existing post-hoc calibration methods yield highly over-confident predictions under domain shift.
Towards Trustworthy Predictions from Deep Neural Networks with Fast Adversarial Calibration
That is, it is crucial for predictive models to be uncertainty-aware and yield well-calibrated (and thus trustworthy) predictions for both in-domain samples as well as under domain shift.
