Introduces courtroom analogy and MoDEX architecture to model classification uncertainty as aggregated Dirichlet opinions from class-specific advocates, claiming SOTA UQ performance and interpretability.
Ensemble distribution distillation
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
MT-BKD applies Bayesian inference with teacher-informed mixture priors and entropy weighting to distill knowledge from multiple teachers, yielding improved accuracy and uncertainty quantification on synthetic and real tasks.
DRD introduces a reprogramming module and CKA-based distillation to enable efficient, robust adaptation of medical foundation models to downstream 2D/3D classification and segmentation tasks, outperforming prior PEFT and KD methods on 18 tasks.
Supervised fine-tuning degrades the correlation between confidence scores and output quality in language models, driven by factors like training distribution similarity rather than true quality.
citing papers explorer
-
Courtroom Analogy: New Perspective on Uncertainty-Aware Classification
Introduces courtroom analogy and MoDEX architecture to model classification uncertainty as aggregated Dirichlet opinions from class-specific advocates, claiming SOTA UQ performance and interpretability.
-
Multi-Teacher Knowledge Distillation via Teacher-Informed Mixture Priors
MT-BKD applies Bayesian inference with teacher-informed mixture priors and entropy weighting to distill knowledge from multiple teachers, yielding improved accuracy and uncertainty quantification on synthetic and real tasks.
-
Deep Reprogramming Distillation for Medical Foundation Models
DRD introduces a reprogramming module and CKA-based distillation to enable efficient, robust adaptation of medical foundation models to downstream 2D/3D classification and segmentation tasks, outperforming prior PEFT and KD methods on 18 tasks.
-
Confident in a Confidence Score: Investigating the Sensitivity of Confidence Scores to Supervised Fine-Tuning
Supervised fine-tuning degrades the correlation between confidence scores and output quality in language models, driven by factors like training distribution similarity rather than true quality.