Adaptive Decoding via Latent Preference Optimization

S Dhuliawala, I Kulikov, P Yu, A Celikyilmaz… - arxiv preprint arxiv …, 2024 - arxiv.org
During language model decoding, it is known that using higher temperature sampling gives
more creative responses, while lower temperatures are more factually accurate. However …

On Uncertainty In Natural Language Processing

D Ulmer - arxiv preprint arxiv:2410.03446, 2024 - arxiv.org
The last decade in deep learning has brought on increasingly capable systems that are
deployed on a wide variety of applications. In natural language processing, the field has …

Optical aberrations in autonomous driving: Physics-informed parameterized temperature scaling for neural network uncertainty calibration

DW Wolf, A Braun, M Ulrich - arxiv preprint arxiv:2412.13695, 2024 - arxiv.org
'A trustworthy representation of uncertainty is desirable and should be considered as a key
feature of any machine learning method'(Huellermeier and Waegeman, 2021). This …