Vector quantization induces a structured partition of the representation space for composing heterogeneous multiclass calibration maps via shared codeword-dependent Dirichlet factors.
arXiv preprint arXiv:2308.01222 (2023)
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
years
2026 8representative citing papers
Inducing artificial uncertainty on trivial tasks allows training probes that achieve higher calibration on hard data than standard approaches while retaining performance on easy data.
Post-hoc calibration of miscalibrated black-box predictions on a labeled sample improves efficiency of prediction-powered inference for semisupervised mean estimation.
Unsupervised single-generation confidence calibration for reasoning LLMs via offline self-consistency proxy distillation outperforms baselines on math and QA tasks and improves selective prediction.
Hard-label delivery via multipass or SLS matches or beats soft-label training on annotator disagreement data when annotations are sparse and leads to flatter minima.
SINAPSE uses a dual-branch neural network with a 1D convolutional autoencoder for denoising and a classifier for neutron-gamma discrimination, trained via random augmentations on high-SNR data and validated with SHAP explanations.
VOLTA, consisting of a deep encoder with learnable prototypes plus cross-entropy and post-hoc temperature scaling, matches or exceeds ten UQ baselines in accuracy, achieves lower expected calibration error, and performs well on out-of-distribution detection across CIFAR, SVHN, and corruption shifts.
citing papers explorer
-
Divide et Calibra: Multiclass Local Calibration via Vector Quantization
Vector quantization induces a structured partition of the representation space for composing heterogeneous multiclass calibration maps via shared codeword-dependent Dirichlet factors.
-
Inducing Artificial Uncertainty in Language Models
Inducing artificial uncertainty on trivial tasks allows training probes that achieve higher calibration on hard data than standard approaches while retaining performance on easy data.
-
Calibeating Prediction-Powered Inference
Post-hoc calibration of miscalibrated black-box predictions on a labeled sample improves efficiency of prediction-powered inference for semisupervised mean estimation.
-
Unsupervised Confidence Calibration for Reasoning LLMs from a Single Generation
Unsupervised single-generation confidence calibration for reasoning LLMs via offline self-consistency proxy distillation outperforms baselines on math and QA tasks and improves selective prediction.
-
Same Target, Different Basins: Hard vs. Soft Labels for Annotator Distributions
Hard-label delivery via multipass or SLS matches or beats soft-label training on annotator disagreement data when annotations are sparse and leads to flatter minima.
-
SINAPSE: A lightweight deep learning framework for accurate and explainable neutron-$\gamma$ discrimination
SINAPSE uses a dual-branch neural network with a 1D convolutional autoencoder for denoising and a classifier for neutron-gamma discrimination, trained via random augmentations on high-SNR data and validated with SHAP explanations.
-
VOLTA: The Surprising Ineffectiveness of Auxiliary Losses for Calibrated Deep Learning
VOLTA, consisting of a deep encoder with learnable prototypes plus cross-entropy and post-hoc temperature scaling, matches or exceeds ten UQ baselines in accuracy, achieves lower expected calibration error, and performs well on out-of-distribution detection across CIFAR, SVHN, and corruption shifts.
- Look-Closer-Then-Diagnose: Confidence-Aware Ultrasound VQA via Active Zooming