Related papers: Calibrated Abstention for Reliable TCR--pMHC Bindi…
Reliable probabilities are critical in high-risk applications, yet common calibration criteria (confidence, class-wise) are only necessary for full distributional calibration, and post-hoc methods often lack distribution-free guarantees. We…
Modern language models fail a fundamental requirement of trustworthy intelligence: knowing when not to answer. Despite achieving impressive accuracy on benchmarks, these models produce confident hallucinations, even when wrong answers carry…
Motivation: Peptide-protein interactions (PepPIs) are central to cellular regulation and peptide therapeutics, but experimental characterization remains too slow for large-scale screening. Existing methods usually emphasize either…
To build robust, fair, and safe AI systems, we would like our classifiers to say ``I don't know'' when facing test examples that are difficult or fall outside of the training classes.The ubiquitous strategy to predict under uncertainty is…
The major histocompatibility complex (MHC) molecules, which bind peptides for presentation on the cell surface, play an important role in cell-mediated immunity. In light of developing databases and technologies over the years, significant…
Click-Through Rate (CTR) prediction, crucial in applications like recommender systems and online advertising, involves ranking items based on the likelihood of user clicks. User behavior sequence modeling has marked progress in CTR…
Confidence calibration has been dominated by the Expected Calibration Error (ECE), a linear metric that counts calibration offset equally regardless of the confidence level at which it occurs. We show that ECE can remain small even under…
As an autonomous system performs a task, it should maintain a calibrated estimate of the probability that it will achieve the user's goal. If that probability falls below some desired level, it should alert the user so that appropriate…
Deep learning models often achieve expert-level accuracy in medical image classification but suffer from a critical flaw: semantic incoherence. These high-confidence mistakes that are semantically incoherent (e.g., classifying a malignant…
Attention-based methods and Connectionist Temporal Classification (CTC) network have been promising research directions for end-to-end Automatic Speech Recognition (ASR). The joint CTC/Attention model has achieved great success by utilizing…
Personalized intervention strategies, in particular those that modify treatment based on a participant's own response, are a core component of precision medicine approaches. Sequential Multiple Assignment Randomized Trials (SMARTs) are…
We present a model predictive control (MPC) framework for nonlinear stochastic systems that ensures safety guarantee with high probability. Unlike most existing stochastic MPC schemes, our method adopts a set-erosion that converts the…
To ensure faithful information transmission, cells utilize nonequilibrium drives to reduce errors. Kinetic proofreading is a classic mechanism known to sharpen ligand discrimination by T lymphocytes. It remains an open question whether the…
In typical machine learning systems, an estimate of the probability of the prediction is used to assess the system's confidence in the prediction. This confidence measure is usually uncalibrated; i.e.\ the system's confidence in the…
Confidence calibration for classification models is vital in safety-critical decision-making scenarios and has received extensive attention. General confidence calibration methods assume training and test data are independent and…
Uncertainty quantification of machine learning and deep learning methods plays an important role in enhancing trust to the obtained result. In recent years, a numerous number of uncertainty quantification methods have been introduced. Monte…
A robust adaptive model predictive control (MPC) algorithm is presented for linear, time invariant systems with unknown dynamics and subject to bounded measurement noise. The system is characterized by an impulse response model, which is…
This research aims to explore the intersection of Large Language Models and confidence calibration in Entity Matching. To this end, we perform an empirical study to compare baseline RoBERTa confidences for an Entity Matching task against…
Background: Electrocardiograms are indispensable for diagnosing cardiovascular diseases, yet in many settings they exist only as paper printouts stored in multiple recording layouts. Converting these images into digital signals introduces…
Despite extensive research on neural network calibration, existing methods typically apply global transformations that treat all predictions uniformly, overlooking the heterogeneous reliability of individual predictions. Furthermore, the…