arXiv Machine Learning
Bridging the Confidence Gap: Temperature Scaling for Calibrating Test-Time Prompt Tuning
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Sep 1
Rethinking the Test-Time Prompt Tuning Objective from the Perspective of Calibration
arXiv:2608.30230v1 Announce Type: new Abstract: Test-time prompt tuning (TPT) has emerged as a powerful paradigm, refining prompts for each test sample via entropy minimization (EM) over multiple aug...
arXiv AI
Jun 2
CalArena: A Large-Scale Post-Hoc Calibration Benchmark
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 Machine Learning
Aug 27
Sample Margin-Aware Recalibration of Temperature Scaling
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 Machine Learning
Jul 10
LiST: Lipschitz Scaling Training for Robust and Calibrated Neural Networks
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.
arXiv Machine Learning
Oct 12
Optimizable Model Averaging for Ensembling Heterogeneous Model Outputs
Optimizable Model Averaging (OMA) is a black‑box method that assigns nonnegative weights to each candidate model’s predictive probabilities, keeping all model parameters frozen. By minimizing regularized predictive entropy, OMA learns a single scalar coefficient per model to average outputs from heterogeneous architectures. The authors show that appropriate regularization reduces expected calibration error and improves the trade‑off between performance and calibration compared to simple output averaging.
arXiv Machine Learning
Aug 12
Invertible Logits Transformation for Accuracy-Preserving Post-Hoc Uncertainty Calibration
arXiv:2608. 10372v1 Announce Type: new Abstract: Post-hoc calibration aligns a classifier's predicted confidences with its empirical accuracy without retraining.