相关论文: The Well-Tempered Classifier: Some Elementary Prop…

Large Language Models (LLMs) have significantly advanced sentiment analysis, yet their inherent uncertainty and variability pose critical challenges to achieving reliable and consistent outcomes. This paper systematically explores the Model…

Algorithms for simulating complex physical systems or solving difficult optimization problems often resort to an annealing process. Rather than simulating the system at the temperature of interest, an annealing algorithm starts at a…

Uncertainty quantification is a central challenge in reliable and trustworthy machine learning. Naive measures such as last-layer scores are well-known to yield overconfident estimates in the context of overparametrized neural networks.…

The effectiveness of large language models (LLMs) is not only measured by their ability to generate accurate outputs but also by their calibration-how well their confidence scores reflect the probability of their outputs being correct.…

Prior work has explored directly regularizing the output distributions of probabilistic models to alleviate peaky (i.e. over-confident) predictions, a common sign of overfitting. This class of techniques, of which label smoothing is one,…

Dataset scaling, also known as normalization, is an essential preprocessing step in a machine learning pipeline. It is aimed at adjusting attributes scales in a way that they all vary within the same range. This transformation is known to…

Pre-trained language models (PLMs) may fail in giving reliable estimates of their predictive uncertainty. We take a close look into this problem, aiming to answer two questions: (1) Do PLMs learn to become calibrated in the training…

As performance gains through scaling data and/or model size experience diminishing returns, it is becoming increasingly popular to turn to ensembling, where the predictions of multiple models are combined to improve accuracy. In this paper,…

Accurately quantifying uncertainty in large language models (LLMs) is crucial for their reliable deployment, especially in high-stakes applications. Current state-of-the-art methods for measuring semantic uncertainty in LLMs rely on strict…

While the accuracy of modern deep learning models has significantly improved in recent years, the ability of these models to generate uncertainty estimates has not progressed to the same degree. Uncertainty methods are designed to provide…

Large language models (LLMs) have achieved remarkable results in wide range of domains. However, the accuracy and robustness of one-shot LLM predictions remain highly sensitive to the examples and the diversity among ensemble members. This…

Large language models (LLMs) are increasingly employed in information-seeking and decision-making tasks. Despite their broad utility, LLMs tend to generate information that conflicts with real-world facts, and their persuasive style can…

Representing a true label as a one-hot vector is a common practice in training text classification models. However, the one-hot representation may not adequately reflect the relation between the instances and labels, as labels are often not…

Metric learning aims at learning a distance which is consistent with the semantic meaning of the samples. The problem is generally solved by learning an embedding for each sample such that the embeddings of samples of the same category are…

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…

Calibration is a frequently invoked concept when useful label probability estimates are required on top of classification accuracy. A calibrated model is a function whose values correctly reflect underlying label probabilities. Calibration…

A formal linear vector field representation for scientific equations is developed to rationalize the intuitive methods that are constantly employed. It is shown that unlike mechanical units that appear in the basis of the space, the reduced…

Active thermal control is crucial in achieving the required accuracy and throughput in many industrial applications, e.g., in the medical industry, high-power lighting industry, and semiconductor industry. Thermoelectric Modules (TEMs) can…

Weather is a phenomenon that affects everything and everyone around us on a daily basis. Weather prediction has been an important point of study for decades as researchers have tried to predict the weather and climatic changes using…

In finite-size scaling analyses of Monte Carlo simulations of second-order phase transitions one often needs an extended temperature range around the critical point. By combining the parallel tempering algorithm with cluster updates and an…