Image de couverture de livre

Beyond Overconfidence: Foundation Models Redefine Calibration in Deep Neural Networks

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Hekler, Achim, Kuhn, Lukas, Buettner, Florian
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

From Entropy to Calibrated Uncertainty: Training Language Models to Reason About Uncertainty
par: Jenane, Azza, et autres
Publié: (2026)

Better Uncertainty Calibration via Proper Scores for Classification and Beyond
par: Gruber, Sebastian G., et autres
Publié: (2022)

DATS: Distance-Aware Temperature Scaling for Calibrated Class-Incremental Learning
par: Serra, Giuseppe, et autres
Publié: (2025)

Federated Continual Learning Goes Online: Uncertainty-Aware Memory Management for Vision Tasks and Beyond
par: Serra, Giuseppe, et autres
Publié: (2024)

Improving Perturbation-based Explanations by Understanding the Role of Uncertainty Calibration
par: Decker, Thomas, et autres
Publié: (2025)

Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations
par: Decker, Thomas, et autres
Publié: (2025)

A Bias-Variance-Covariance Decomposition of Kernel Scores for Generative Models
par: Gruber, Sebastian G., et autres
Publié: (2023)

MoRE-LLM: Mixture of Rule Experts Guided by a Large Language Model
par: Koebler, Alexander, et autres
Publié: (2025)

Efficient Unsupervised Shortcut Learning Detection and Mitigation in Transformers
par: Kuhn, Lukas, et autres
Publié: (2025)

Overconfidence and Calibration in Medical VQA: Empirical Findings and Hallucination-Aware Mitigation
par: Byun, Ji Young, et autres
Publié: (2026)

LLMs are Overconfident: Evaluating Confidence Interval Calibration with FermiEval
par: Epstein, Elliot L., et autres
Publié: (2025)

How to Leverage Predictive Uncertainty Estimates for Reducing Catastrophic Forgetting in Online Continual Learning
par: Serra, Giuseppe, et autres
Publié: (2024)

Mind the Gap: A Framework for Assessing Pitfalls in Multimodal Active Learning
par: Eisenhardt, Dustin, et autres
Publié: (2026)

Humble your Overconfident Networks: Unlearning Overfitting via Sequential Monte Carlo Tempered Deep Ensembles
par: Millard, Andrew, et autres
Publié: (2025)

Proximity-Informed Calibration for Deep Neural Networks
par: Xiong, Miao, et autres
Publié: (2023)

Beyond Accuracy: Are Time Series Foundation Models Well-Calibrated?
par: Adler, Coen, et autres
Publié: (2025)

Enhancing Deep Neural Network Reliability with Refinement and Calibration
par: Hebbalaguppe, Ramya, et autres
Publié: (2026)

DeepCSHAP: Utilizing Shapley Values to Explain Deep Complex-Valued Neural Networks
par: Eilers, Florian, et autres
Publié: (2024)

Deep Neural Network Calibration by Reducing Classifier Shift with Stochastic Masking
par: Ni, Jiani, et autres
Publié: (2025)

Machine Learning based Analysis for Radiomics Features Robustness in Real-World Deployment Scenarios
par: Khan, Sarmad Ahmad, et autres
Publié: (2025)

The Cost of Reasoning: Chain-of-Thought Induces Overconfidence in Vision-Language Models
par: Welch, Robert, et autres
Publié: (2026)

An autonomous agent for auditing and improving the reliability of clinical AI models
par: Kuhn, Lukas, et autres
Publié: (2025)

Continuous-Time Piecewise-Linear Recurrent Neural Networks
par: Brändle, Alena, et autres
Publié: (2026)

Explanatory Model Monitoring to Understand the Effects of Feature Shifts on Performance
par: Decker, Thomas, et autres
Publié: (2024)

ForecastGrapher: Redefining Multivariate Time Series Forecasting with Graph Neural Networks
par: Cai, Wanlin, et autres
Publié: (2024)

Growing with Experience: Growing Neural Networks in Deep Reinforcement Learning
par: Fehring, Lukas, et autres
Publié: (2025)

Agentic Uncertainty Reveals Agentic Overconfidence
par: Kaddour, Jean, et autres
Publié: (2026)

Overconfident Oracles: Limitations of In Silico Sequence Design Benchmarking
par: Surana, Shikha, et autres
Publié: (2025)

Calibrating Deep Neural Network using Euclidean Distance
par: Liang, Wenhao, et autres
Publié: (2024)

SpectrumFM: Redefining Spectrum Cognition via Foundation Modeling
par: Liu, Chunyu, et autres
Publié: (2025)

Disentangling Mean Embeddings for Better Diagnostics of Image Generators
par: Gruber, Sebastian G., et autres
Publié: (2024)

Beyond Over-smoothing: Uncovering the Trainability Challenges in Deep Graph Neural Networks
par: Peng, Jie, et autres
Publié: (2024)

Rethinking Calibration for Early-Exit Neural Networks
par: Kubaty, Piotr, et autres
Publié: (2025)

Probabilistic Calibration by Design for Neural Network Regression
par: Dheur, Victor, et autres
Publié: (2024)

Uncalibrated Reasoning: GRPO Induces Overconfidence for Stochastic Outcomes
par: Bereket, Michael, et autres
Publié: (2025)

Fine-Grained Uncertainty Decomposition in Large Language Models: A Spectral Approach
par: Walha, Nassim, et autres
Publié: (2025)

Incremental Uncertainty-aware Performance Monitoring with Active Labeling Intervention
par: Koebler, Alexander, et autres
Publié: (2025)

Rule Based Learning with Dynamic (Graph) Neural Networks
par: Seiffarth, Florian
Publié: (2024)

Grokking Beyond Neural Networks: An Empirical Exploration with Model Complexity
par: Miller, Jack, et autres
Publié: (2023)

Mitigating Overconfidence in Out-of-Distribution Detection by Capturing Extreme Activations
par: Azizmalayeri, Mohammad, et autres
Publié: (2024)