English
Related papers

Related papers: Sample Margin-Aware Recalibration of Temperature S…

200 papers

Neural networks solving real-world problems are often required not only to make accurate predictions but also to provide a confidence level in the forecast. The calibration of a model indicates how close the estimated confidence is to the…

Neural and Evolutionary Computing · Computer Science 2023-03-21 Ruslan Vasilev , Alexander D'yakonov

A framework for online simultaneous localization, mapping and self-calibration is presented which can detect and handle significant change in the calibration parameters. Estimates are computed in constant-time by factoring the problem and…

Computer Vision and Pattern Recognition · Computer Science 2014-11-06 Nima Keivan , Gabe Sibley

Confidence calibration is an emerging challenge in real-world decision systems based on foundations models when used for downstream vision classification tasks. Due to various reasons exposed, logit scores on the CLIP head remain large…

Computer Vision and Pattern Recognition · Computer Science 2025-09-26 Behraj Khan , Tahir Syed

Large language models have been widely applied to sequential recommendation tasks, yet during inference, they continue to rely on decoding strategies developed for natural language processing. This creates a mismatch between text-generation…

Information Retrieval · Computer Science 2025-09-01 Chenke Yin , Li Fan , Jia Wang , Dongxiao Hu , Haichao Zhang , Chong Zhang , Yang Xiang

Many applications of classification methods not only require high accuracy but also reliable estimation of predictive uncertainty. However, while many current classification frameworks, in particular deep neural networks, achieve high…

Machine Learning · Computer Science 2020-02-28 Jonathan Wenger , Hedvig Kjellström , Rudolph Triebel

Precise confidence estimation in deep learning is vital for high-stakes fields like medical imaging, where overconfident misclassifications can have serious consequences. This work evaluates the effectiveness of Temperature Scaling (TS), a…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Ankur Chanda , Kushan Choudhury , Shubhrodeep Roy , Shubhajit Biswas , Somenath Kuiry

For interpreting the behavior of a probabilistic model, it is useful to measure a model's calibration--the extent to which it produces reliable confidence scores. We address the open problem of calibration for tagging models with sparse…

Computation and Language · Computer Science 2023-05-18 Michael Kranzlein , Nelson F. Liu , Nathan Schneider

Inference-time alignment techniques offer a lightweight alternative or complement to costly reinforcement learning, while enabling continual adaptation as alignment objectives and reward targets evolve. Existing theoretical analyses justify…

Machine Learning · Computer Science 2026-05-14 Ye Wang , Jing Liu , Toshiaki Koike-Akino

Accurate and reliable probability predictions are essential for multi-class supervised learning tasks, where well-calibrated models enable rational decision-making. While isotonic regression has proven effective for binary calibration, its…

Machine Learning · Computer Science 2025-12-11 Alon Arad , Saharon Rosset

Consider a multi-class labelling problem, where the labels can take values in $[k]$, and a predictor predicts a distribution over the labels. In this work, we study the following foundational question: Are there notions of multi-class…

Machine Learning · Computer Science 2024-06-11 Parikshit Gopalan , Lunjia Hu , Guy N. Rothblum

Modern neural networks can achieve high accuracy while remaining poorly calibrated, producing confidence estimates that do not match empirical correctness. Yet calibration is often treated as a post-hoc attribute. We take a different…

Machine Learning · Computer Science 2026-04-23 Alessandro Morosini , Matea Gjika , Tomaso Poggio , Pierfrancesco Beneventano

State-of-the-art semi-supervised learning (SSL) approaches rely on highly confident predictions to serve as pseudo-labels that guide the training on unlabeled samples. An inherent drawback of this strategy stems from the quality of the…

Machine Learning · Computer Science 2024-03-26 Shambhavi Mishra , Balamurali Murugesan , Ismail Ben Ayed , Marco Pedersoli , Jose Dolz

Leveraging the models' outputs, specifically the logits, is a common approach to estimating the test accuracy of a pre-trained neural network on out-of-distribution (OOD) samples without requiring access to the corresponding ground truth…

Machine Learning · Computer Science 2024-11-26 Renchunzi Xie , Ambroise Odonnat , Vasilii Feofanov , Weijian Deng , Jianfeng Zhang , Bo An

LLM-based mutation testing is a promising testing technology, but existing approaches typically rely on a fixed set of mutations as few-shot examples or none at all. This can result in generic low-quality mutations, missed context-specific…

Software Engineering · Computer Science 2026-03-26 Bo Wang , Ming Deng , Mingda Chen , Chengran Yang , Youfang Lin , Mark Harman , Mike Papadakis , Jie M. Zhang

Large language models (LLMs) are evaluated for calibration using metrics such as Expected Calibration Error that conflate two distinct components: the model's ability to discriminate correct from incorrect answers (sensitivity) and its…

Computation and Language · Computer Science 2026-03-17 Jon-Paul Cacioli

Miscalibration - a mismatch between a model's confidence and its correctness - of Deep Neural Networks (DNNs) makes their predictions hard to rely on. Ideally, we want networks to be accurate, calibrated and confident. We show that, as…

Machine Learning · Computer Science 2020-10-27 Jishnu Mukhoti , Viveka Kulharia , Amartya Sanyal , Stuart Golodetz , Philip H. S. Torr , Puneet K. Dokania

Machine learning classifiers often produce probabilistic predictions that are critical for accurate and interpretable decision-making in various domains. The quality of these predictions is generally evaluated with proper losses, such as…

Machine Learning · Computer Science 2025-06-26 Eugène Berta , David Holzmüller , Michael I. Jordan , Francis Bach

A well-calibrated neural model produces confidence (probability outputs) closely approximated by the expected accuracy. While prior studies have shown that mixup training as a data augmentation technique can improve model calibration on…

Computation and Language · Computer Science 2022-03-16 Seo Yeon Park , Cornelia Caragea

We propose SALT (Split-Adaptive Lightweight Tuning), a lightweight model adaptation framework for Split Computing under closed constraints, where the head and tail networks are proprietary and inaccessible to users. In such closed…

Machine Learning · Computer Science 2025-06-17 Yuya Okada , Takayuki Nishio

Reliable uncertainty estimation is critical for deploying neural networks (NNs) in real-world applications. While existing calibration techniques often rely on post-hoc adjustments or coarse-grained binning methods, they remain limited in…

Machine Learning · Computer Science 2025-05-30 Pedro Mendes , Paolo Romano , David Garlan