10 citations · 17 across the 7 of their papers we have counts for
8 papers
Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations
Christian Tomani, Kamalika Chaudhuri, Ivan Evtimov +2
A major barrier towards the practical deployment of large language models (LLMs) is their lack of reliability. Three situations where this is particularly apparent are correctness,…
Quality-Aware Translation Models: Efficient Generation and Quality Estimation in a Single Model
Christian Tomani, David Vilar, Markus Freitag +5
Maximum-a-posteriori (MAP) decoding is the most widely used decoding strategy for neural machine translation (NMT) models. The underlying assumption is that model probability corre…
Beyond In-Domain Scenarios: Robust Density-Aware Calibration
Christian Tomani, Futa Waseda, Yuesong Shen +1
Calibrating deep learning models to yield uncertainty-aware predictions is crucial as deep neural networks get increasingly deployed in safety-critical applications. While existing…
What Makes Graph Neural Networks Miscalibrated?
Hans Hao-Hsun Hsu, Yuesong Shen, Christian Tomani +1
Given the importance of getting calibrated predictions and reliable uncertainty estimations, various post-hoc calibration methods have been developed for neural networks on standar…
CHALLENGER: Training with Attribution Maps
Christian Tomani, Daniel Cremers
We show that utilizing attribution maps for training neural networks can improve regularization of models and thus increase performance. Regularization is key in deep learning, esp…
Parameterized Temperature Scaling for Boosting the Expressive Power in Post-Hoc Uncertainty Calibration
Christian Tomani, Daniel Cremers, Florian Buettner
We address the problem of uncertainty calibration and introduce a novel calibration method, Parametrized Temperature Scaling (PTS). Standard deep neural networks typically yield un…
Post-hoc Uncertainty Calibration for Domain Drift Scenarios
Christian Tomani, Sebastian Gruber, Muhammed Ebrar Erdem +2
We address the problem of uncertainty calibration. While standard deep neural networks typically yield uncalibrated predictions, calibrated confidence scores that are representativ…
Towards Trustworthy Predictions from Deep Neural Networks with Fast Adversarial Calibration
Christian Tomani, Florian Buettner
To facilitate a wide-spread acceptance of AI systems guiding decision making in real-world applications, trustworthiness of deployed models is key. That is, it is crucial for predi…