Logit-Based Ensemble Distribution Distillation for Robust Autoregressive
Sequence Uncertainties

Logit-Based Ensemble Distribution Distillation for Robust Autoregressive Sequence Uncertainties

Conference on Uncertainty in Artificial Intelligence (UAI), 2023

17 May 2023

Yassir Fathullah

ArXiv (abs)PDF HTML

Papers citing "Logit-Based Ensemble Distribution Distillation for Robust Autoregressive Sequence Uncertainties"

4 / 4 papers shown

Title
Improving the Calibration of Confidence Scores in Text Generation Using the Output Distribution's CharacteristicsAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 Lorenzo Jaime Yu Flores Ori Ernst Jackie Chi Kit Cheung 216 0 0 31 May 2025
Who Needs Decoders? Efficient Estimation of Sequence-level AttributesConference of the European Chapter of the Association for Computational Linguistics (EACL), 2023 Yassir Fathullah Puria Radmard Adian Liusie Mark Gales OODD 162 1 0 09 May 2023
Window-Based Early-Exit Cascades for Uncertainty Estimation: When Deep Ensembles are More Efficient than Single ModelsIEEE International Conference on Computer Vision (ICCV), 2023 Guoxuan Xia C. Bouganis UQCV 464 14 0 14 Mar 2023
Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness Jeremiah Zhe Liu Zi Lin Shreyas Padhy Dustin Tran Tania Bedrax-Weiss Balaji Lakshminarayanan UQCV BDL 747 514 0 17 Jun 2020