English
Related papers

Related papers: Posterior Calibrated Training on Sentence Classifi…

200 papers

Although deep neural networks (DNNs) achieve high predictive accuracy, their confidence estimates are often unreliable, potentially compromising user trust in their decisions. This has motivated research on calibrated models, where…

Machine Learning · Computer Science 2026-05-25 Ramya Hebbalaguppe , Ajay Shastry , Soumya Suvra Ghosal , Chetan Arora

Recent works have shown that deep neural networks can achieve super-human performance in a wide range of image classification tasks in the medical imaging domain. However, these works have primarily focused on classification accuracy,…

Computer Vision and Pattern Recognition · Computer Science 2020-09-10 Gongbo Liang , Yu Zhang , Xiaoqin Wang , Nathan Jacobs

The prediction accuracy of machine learning methods is steadily increasing, but the calibration of their uncertainty predictions poses a significant challenge. Numerous works focus on obtaining well-calibrated predictive models, but less is…

Machine Learning · Statistics 2023-12-07 Donghwan Lee , Xinmeng Huang , Hamed Hassani , Edgar Dobriban

Many large-scale machine learning problems involve estimating an unknown parameter $\theta_{i}$ for each of many items. For example, a key problem in sponsored search is to estimate the click through rate (CTR) of each of billions of…

Applications · Statistics 2015-11-27 Omkar Muralidharan , Amir Najmi

Pretrained multilingual encoder models can directly perform zero-shot multilingual tasks or linguistic probing by reformulating the input examples into cloze-style prompts. This is accomplished by predicting the probabilities of the label…

Computation and Language · Computer Science 2023-10-20 Ercong Nie , Helmut Schmid , Hinrich Schütze

Online alignment in machine translation refers to the task of aligning a target word to a source word when the target sequence has only been partially decoded. Good online alignments facilitate important applications such as lexically…

Computation and Language · Computer Science 2022-04-05 Soumya Chatterjee , Sunita Sarawagi , Preethi Jyothi

Meta-Learning aims to speed up the learning process on new tasks by acquiring useful inductive biases from datasets of related learning tasks. While, in practice, the number of related tasks available is often small, most of the existing…

Machine Learning · Statistics 2023-12-27 Jonas Rothfuss , Martin Josifoski , Vincent Fortuin , Andreas Krause

While deep learning models often achieve high predictive accuracy, their predictions typically do not come with any provable guarantees on risk or reliability, which are critical for deployment in high-stakes applications. The framework of…

Machine Learning · Computer Science 2025-10-13 Christopher Yeh , Nicolas Christianson , Adam Wierman , Yisong Yue

Continual learning requires models to integrate new classes or domains over time while preserving previously acquired knowledge. Within this paradigm, foundation models often achieve strong performance, but they still remain subject to the…

Machine Learning · Computer Science 2026-02-20 Murat Onur Yildirim , Elif Ceren Gok Yildirim , Joaquin Vanschoren

Discovery of an accurate causal Bayesian network structure from observational data can be useful in many areas of science. Often the discoveries are made under uncertainty, which can be expressed as probabilities. To guide the use of such…

Artificial Intelligence · Computer Science 2017-12-27 Fattaneh Jabbari , Mahdi Pakdaman Naeini , Gregory F. Cooper

Theoretical guarantees for causal inference using propensity scores are partly based on the scores behaving like conditional probabilities. However, scores between zero and one, especially when outputted by flexible statistical estimators,…

Methodology · Statistics 2024-11-12 Rom Gutman , Ehud Karavani , Yishai Shimoni

Machine-generated probability predictions are essential in modern classification tasks such as image classification. A model is well calibrated when its predicted probabilities correspond to observed event frequencies. Despite the need for…

Machine Learning · Statistics 2026-02-24 Amy Vennos , Xin Xing , Christopher T. Franck

The Superficial Alignment Hypothesis posits that almost all of a language model's abilities and knowledge are learned during pre-training, while post-training is about giving a model the right style and format. We re-examine these claims by…

Computation and Language · Computer Science 2024-10-08 Mohit Raghavendra , Vaskar Nath , Sean Hendryx

Class probabilities predicted by most multiclass classifiers are uncalibrated, often tending towards over-confidence. With neural networks, calibration can be improved by temperature scaling, a method to learn a single corrective…

Machine Learning · Computer Science 2019-10-29 Meelis Kull , Miquel Perello-Nieto , Markus Kängsepp , Telmo Silva Filho , Hao Song , Peter Flach

Large language models (LLMs) exhibit persistent miscalibration, especially after instruction tuning and preference alignment. Modified training objectives can improve calibration, but retraining is expensive. Inference-time steering offers…

Machine Learning · Computer Science 2026-02-06 Miranda Muqing Miao , Young-Min Cho , Lyle Ungar

Probabilistic forecasts are typically obtained using state-of-the-art statistical and machine learning models, with model parameters estimated by optimizing a proper scoring rule over a set of training data. If the model class is not…

Applications · Statistics 2026-05-05 Jakob Benjamin Wessel , Maybritt Schillinger , Frank Kwasniok , Sam Allen

While large language models (LLMs) have demonstrated remarkable capabilities in language modeling, recent studies reveal that they often fail on out-of-distribution (OOD) samples due to spurious correlations acquired during pre-training.…

Machine Learning · Computer Science 2025-06-12 Shurui Gui , Shuiwang Ji

While the predictions produced by conformal prediction are set-valued, the data used for training and calibration is supposed to be precise. In the setting of superset learning or learning from partial labels, a variant of weakly supervised…

Machine Learning · Computer Science 2023-06-05 Alireza Javanmardi , Yusuf Sale , Paul Hofman , Eyke Hüllermeier

Risk assessments to help inform criminal justice decisions have been used in the United States since the 1920s. Over the past several years, statistical learning risk algorithms have been introduced amid much controversy about fairness,…

Methodology · Statistics 2021-04-20 Arun K. Kuchibhotla , Richard A. Berk

Probabilistic predictions from neural networks which account for predictive uncertainty during classification is crucial in many real-world and high-impact decision making settings. However, in practice most datasets are trained on…

Machine Learning · Computer Science 2022-09-30 Satya Borgohain , Klaus Ackermann , Ruben Loaiza-Maya