Cover Image

Calibrating LLMs with Information-Theoretic Evidential Deep Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Yawei, Rügamer, David, Bischl, Bernd, Rezaei, Mina
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Deep Weight Factorization: Sparse Learning Through the Lens of Artificial Symmetries
by: Kolb, Chris, et al.
Published: (2025)

Structured Credal Learning
by: Venkatesh, Varun, et al.
Published: (2026)

A Dual-Perspective Approach to Evaluating Feature Attribution Methods
by: Li, Yawei, et al.
Published: (2023)

Differentiable Sparsity via $D$-Gating: Simple and Versatile Structured Penalization
by: Kolb, Chris, et al.
Published: (2025)

Uncertainty-aware Pseudo-label Selection for Positive-Unlabeled Learning
by: Dorigatti, Emilio, et al.
Published: (2022)

Revisiting Unbiased Implicit Variational Inference
by: Pielok, Tobias, et al.
Published: (2025)

Post-hoc Orthogonalization for Mitigation of Protected Feature Bias in CXR Embeddings
by: Weber, Tobias, et al.
Published: (2023)

Semi-Implicit Variational Inference via Kernelized Path Gradient Descent
by: Pielok, Tobias, et al.
Published: (2025)

FinerCut: Finer-grained Interpretable Layer Pruning for Large Language Models
by: Zhang, Yang, et al.
Published: (2024)

AttributionLab: Faithfulness of Feature Attribution Under Controllable Environments
by: Zhang, Yang, et al.
Published: (2023)

Smoothing the Edges: Smooth Optimization for Sparse Regularization using Hadamard Overparametrization
by: Kolb, Chris, et al.
Published: (2023)

On Training Survival Models with Scoring Rules
by: Kopper, Philipp, et al.
Published: (2024)

Connecting the Dots: Is Mode-Connectedness the Key to Feasible Sample-Based Inference in Bayesian Neural Networks?
by: Sommer, Emanuel, et al.
Published: (2024)

Domain Adaptation for Time-Series Classification to Mitigate Covariate Shift
by: Ott, Felix, et al.
Published: (2022)

Position: The Time for Sampling Is Now! Charting a New Course for Bayesian Deep Learning
by: Sommer, Emanuel, et al.
Published: (2026)

Density-Informed Pseudo-Counts for Calibrated Evidential Deep Learning
by: Carlotti, Pietro, et al.
Published: (2026)

Deep Learning for Survival Analysis: A Review
by: Wiegrebe, Simon, et al.
Published: (2023)

Trust Me, I Know the Way: Predictive Uncertainty in the Presence of Shortcut Learning
by: Wimmer, Lisa, et al.
Published: (2025)

mlr3torch: A Deep Learning Framework in R based on mlr3 and torch
by: Fischer, Sebastian, et al.
Published: (2026)

Benchmarking Online Sequence-to-Sequence and Character-based Handwriting Recognition from IMU-Enhanced Pens
by: Ott, Felix, et al.
Published: (2022)

Scalable Higher-Order Tensor Product Spline Models
by: Rügamer, David
Published: (2024)

Revisiting Theory of Contrastive Learning for Domain Generalization
by: Alvandi, Ali, et al.
Published: (2025)

Position: Why We Must Rethink Empirical Research in Machine Learning
by: Herrmann, Moritz, et al.
Published: (2024)

Overtuning in Hyperparameter Optimization
by: Schneider, Lennart, et al.
Published: (2025)

Uncertainty Estimation by Flexible Evidential Deep Learning
by: Yoon, Taeseong, et al.
Published: (2025)

Bi-level Meta-Policy Control for Dynamic Uncertainty Calibration in Evidential Deep Learning
by: Yang, Zhen, et al.
Published: (2025)

On the Epistemic Uncertainty of Overparametrized Neural Networks
by: Rügamer, David
Published: (2026)

Uncertainty Estimation by Density Aware Evidential Deep Learning
by: Yoon, Taeseong, et al.
Published: (2024)

Echoes of Socratic Doubt: Embracing Uncertainty in Calibrated Evidential Reinforcement Learning
by: Stutts, Alex Christopher, et al.
Published: (2024)

Equivariant Evidential Deep Learning for Interatomic Potentials
by: Wang, Zhongyao, et al.
Published: (2026)

Additive Model Boosting: New Insights and Path(ologie)s
by: Schulte, Rickmer, et al.
Published: (2025)

Rethinking Intrinsic Dimension Estimation in Neural Representations
by: Schulte, Rickmer, et al.
Published: (2026)

Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage?
by: Shen, Maohao, et al.
Published: (2024)

Evidential Deep Learning for Probabilistic Modelling of Extreme Storm Events
by: Khot, Ayush, et al.
Published: (2024)

bde: A Python Package for Bayesian Deep Ensembles via MILE
by: Arvanitis, Vyron, et al.
Published: (2026)

Efficient Document Embeddings via Self-Contrastive Bregman Divergence Learning
by: Saggau, Daniel, et al.
Published: (2023)

Reshuffling Resampling Splits Can Improve Generalization of Hyperparameter Optimization
by: Nagler, Thomas, et al.
Published: (2024)

On the Robustness of Global Feature Effect Explanations
by: Baniecki, Hubert, et al.
Published: (2024)

Efficient and Accurate Explanation Estimation with Distribution Compression
by: Baniecki, Hubert, et al.
Published: (2024)

Revisiting Essential and Nonessential Settings of Evidential Deep Learning
by: Chen, Mengyuan, et al.
Published: (2024)