相关论文: Characterizing Sources of Uncertainty to Proxy Cal…

Trust is a crucial factor affecting the adoption of machine learning (ML) models. Qualitative studies have revealed that end-users, particularly in the medical domain, need models that can express their uncertainty in decision-making…

Due to the steadily increasing relevance of machine learning for practical applications, many of which are coming with safety requirements, the notion of uncertainty has received increasing attention in machine learning research in the last…

Decomposing predictive uncertainty into epistemic (model ignorance) and aleatoric (data ambiguity) components is central to reliable decision making, yet most methods estimate both from the same predictive distribution. Recent empirical and…

Methods for interpreting machine learning black-box models increase the outcomes' transparency and in turn generates insight into the reliability and fairness of the algorithms. However, the interpretations themselves could contain…

High-quality labeled data is essential for training robust machine learning models, yet obtaining annotations at scale remains expensive. AI-assisted annotation has therefore become standard in large-scale labeling workflows. However, in…

Post-hoc explanation methods are widely used to interpret black-box predictions, but their generation is often computationally expensive and their reliability is not guaranteed. We propose epistemic uncertainty as a low-cost proxy for…

Explainable AI has become a common term in the literature, scrutinized by computer scientists and statisticians and highlighted by psychological or philosophical researchers. One major effort many researchers tackle is constructing general…

Modern machine learning methods including deep learning have achieved great success in predictive accuracy for supervised learning tasks, but may still fall short in giving useful estimates of their predictive {\em uncertainty}. Quantifying…

Aggregating multiple annotations into a single ground truth label may hide valuable insights into annotator disagreement, particularly in tasks where subjectivity plays a crucial role. In this work, we explore methods for identifying…

Recently, aspect sentiment quad prediction has received widespread attention in the field of aspect-based sentiment analysis. Existing studies extract quadruplets via pre-trained generative language models to paraphrase the original…

As machine learning and algorithmic decision making systems are increasingly being leveraged in high-stakes human-in-the-loop settings, there is a pressing need to understand the rationale of their predictions. Researchers have responded to…

The inability of artificial neural networks to assess the uncertainty of their predictions is an impediment to their widespread use. We distinguish two types of learnable uncertainty: model uncertainty due to a lack of training data and…

The distribution of a neural network's latent representations has been successfully used to detect out-of-distribution (OOD) data. This work investigates whether this distribution moreover correlates with a model's epistemic uncertainty,…

Many machine learning tasks involve inherent subjectivity, where annotators naturally provide varied labels. Standard practice collapses these label distributions into single labels, aggregating diverse human judgments into point estimates.…

This paper tackles the challenge of detecting unreliable behavior in regression algorithms, which may arise from intrinsic variability (e.g., aleatoric uncertainty) or modeling errors (e.g., model uncertainty). First, we formally introduce…

Machine Translation Quality Estimation is a notoriously difficult task, which lessens its usefulness in real-world translation environments. Such scenarios can be improved if quality predictions are accompanied by a measure of uncertainty.…

Uncertainty Quantification (UQ) is essential in probabilistic machine learning models, particularly for assessing the reliability of predictions. In this paper, we present a systematic framework for estimating both epistemic and aleatoric…

Accurate quantification of model uncertainty has long been recognized as a fundamental requirement for trusted AI. In regression tasks, uncertainty is typically quantified using prediction intervals calibrated to a specific operating point,…

Existing methods for quantifying predictive uncertainty in neural networks are either computationally intractable for large language models or require access to training data that is typically unavailable. We derive a lightweight…

Machine Learning (ML) models are often complex and difficult to interpret due to their 'black-box' characteristics. Interpretability of a ML model is usually defined as the degree to which a human can understand the cause of decisions…