The paper proposes a bilevel Stackelberg formulation that trains standard post‑hoc calibrators end‑to‑end with the neural network backbone, eliminating the need for a separate calibration dataset or dedicated loss. By jointly optimizing accuracy and calibration with cross‑entropy and a single calibrator learning‑rate hyperparameter, the method can use any calibrator type, but shows that the final classification layer alone suffices to produce accurate, well‑calibrated models. This approach outperforms state‑of‑the‑art calibrators while adding minimal complexity and avoiding the overhead of separate calibration components, especially beneficial in multi‑task learning settings.
arXiv:2607. 07745v1 Announce Type: new Abstract: While accuracy, robustness, and calibration are all essential for reliable neural networks, they are often studied separately; developing models that satisfy all three simultaneously remains a central challenge.
The paper introduces SMART, a lightweight recalibration technique that adjusts logits based on the margin between the top two logits, called the logit gap. It uses a soft-binned Expected Calibration Error objective to balance bias and variance, enabling stable updates even with limited calibration data. Experiments across various datasets and architectures show SMART achieves state‑of‑the‑art calibration with fewer parameters than existing methods.
arXiv:2605. 30188v2 Announce Type: replace-cross Abstract: Reliable probability estimates are critical in many machine learning applications, yet modern classifiers are often poorly calibrated.
arXiv:2608. 10372v1 Announce Type: new Abstract: Post-hoc calibration aligns a classifier's predicted confidences with its empirical accuracy without retraining.
arXiv:2610. 09020v1 Announce Type: new Abstract: Modern neural networks are often miscalibrated, with a tendency to overconfidence.
arXiv:2505. 23866v2 Announce Type: replace Abstract: Deep neural networks have been increasingly used in safety-critical applications such as medical diagnosis and autonomous driving.
CORE-STACK+ is a new meta‑learning framework for deep stacked generalization that tackles two key problems in heterogeneous vision ensembles: prediction‑space multicollinearity and calibration collapse. It introduces a four‑step preconditioning pipeline—kernelized redundancy filtering, a lightweight differentiable meta‑feature gate, a spectrum‑adaptive ridge penalty, and a Laplace‑approximate Bayesian blender—to jointly improve conditioning and calibration. Across six vision benchmarks, CORE‑STACK+ boosts accuracy, reduces model count and inference cost, and significantly lowers expected calibration error compared to existing methods.
The paper introduces EUA‑Cal, a calibration method that preserves the early‑training uncertainty of deep neural networks. By regularizing predictions and feature prototypes based on the early model, EUA‑Cal mitigates overconfidence while maintaining accuracy. Experiments on image classification and multiple‑choice question answering across eight models show EUA‑Cal outperforms existing calibration techniques.
arXiv:2606. 28654v1 Announce Type: cross Abstract: Deep Neural Network (DNN) classifiers suffer from poor calibration when their softmax outputs (predictive confidence) deviate from the empirical likelihoods.
arXiv:2512.04305v3 Announce Type: replace Abstract: Vision-language models (VLMs) such as CLIP are increasingly adapted across decentralized data silos, yet the reliability of their predictions under...
arXiv:2608. 07419v1 Announce Type: new Abstract: Preference alignment often makes large language models (LLMs) overconfident and poorly calibrated.
arXiv:2609.17386v1 Announce Type: new Abstract: Test-time prompt tuning (TPT) enables adaptation on a single test instance, achieving improved accuracy but often sacrificing calibration performance....