相关论文: Confidence Calibration under Ambiguous Ground Trut…

We study estimating inherent human disagreement (annotation label distribution) in natural language inference task. Post-hoc smoothing of the predicted label distribution to match the expected label entropy is very effective. Such simple…

Tabular data is one of the most widely used data modalities, encompassing numerous datasets with substantial amounts of unlabeled data. Despite this prevalence, there is a notable lack of simple and versatile methods for utilizing unlabeled…

Label smoothing is widely used in deep neural networks for multi-class classification. While it enhances model generalization and reduces overconfidence by aiming to lower the probability for the predicted class, it distorts the predicted…

To increase the trustworthiness of deep neural network (DNN) classifiers, an accurate prediction confidence that represents the true likelihood of correctness is crucial. Towards this end, many post-hoc calibration methods have been…

Probabilistic classifiers output confidence scores along with their predictions, and these confidence scores should be calibrated, i.e., they should reflect the reliability of the prediction. Confidence scores that minimize standard metrics…

Post-hoc attribution methods aim to explain deep learning predictions by highlighting influential input pixels. However, these explanations are highly non-robust: small, imperceptible input perturbations can drastically alter the…

Calibration strengthens the trustworthiness of black-box models by producing better accurate confidence estimates on given examples. However, little is known about if model explanations can help confidence calibration. Intuitively, humans…

Ensuring that Large Language Models (LLMs) generate summaries faithful to a given source document is essential for real-world applications. While prior research has explored LLM faithfulness, existing benchmarks suffer from annotation…

Training with sparse annotations is known to reduce the performance of object detectors. Previous methods have focused on proxies for missing ground truth annotations in the form of pseudo-labels for unlabeled boxes. We observe that…

For users to trust model predictions, they need to understand model outputs, particularly their confidence - calibration aims to adjust (calibrate) models' confidence to match expected accuracy. We argue that the traditional calibration…

Calibration of deep learning models is crucial to their trustworthiness and safe usage, and as such, has been extensively studied in supervised classification models, with methods crafted to decrease miscalibration. However, there has yet…

The predictive performance of supervised learning algorithms depends on the quality of labels. In a typical label collection process, multiple annotators provide subjective noisy estimates of the "truth" under the influence of their varying…

Mislabeled data is a pervasive issue that undermines the performance of machine learning systems in real-world applications. An effective approach to mitigate this problem is to detect mislabeled instances and subject them to special…

As large language models (LLMs) are increasingly deployed in critical decision-making systems, the lack of reliable methods to measure their uncertainty presents a fundamental trustworthiness risk. We introduce a normalized confidence score…

Medical tasks are prone to inter-rater variability due to multiple factors such as image quality, professional experience and training, or guideline clarity. Training deep learning networks with annotations from multiple raters is a common…

Transformers have had a profound impact on the field of artificial intelligence, especially on large language models and their variants. However, as was the case with neural networks, their black-box nature limits trust and deployment in…

Language models have shown promise in various tasks but can be affected by undesired data during training, fine-tuning, or alignment. For example, if some unsafe conversations are wrongly annotated as safe ones, the model fine-tuned on…

Data verification, the process of labeling data items as correct or incorrect, is a preprocessing step that may critically affect the quality of results in data-driven pipelines. Despite recent advances, verification can still produce…

Fairness in toxicity classification involves three integrated axes: ranking, calibration, and abstention. Training-time interventions and post-hoc safety mechanisms cannot be evaluated independently because the former determines the…

In the e-commerce advertising scenario, estimating the true probabilities (known as a calibrated estimate) on Click-Through Rate (CTR) and Conversion Rate (CVR) is critical. Previous research has introduced numerous solutions for addressing…