8 papers
Invertible Logits Transformation for Accuracy-Preserving Post-Hoc Uncertainty Calibration
Lening Zhao, Qipeng Zhan, Li Shen
Post-hoc calibration aligns a classifier's predicted confidences with its empirical accuracy without retraining. An ideal calibrator should correct nonlinear miscalibration, scale…
Stochastic Regret Guarantees for Online Zeroth- and First-Order Bilevel Optimization
Parvin Nazari, Bojian Hou, Davoud Ataee Tarzanagh +2
Online bilevel optimization (OBO) is a powerful framework for machine learning problems where both outer and inner objectives evolve over time, requiring dynamic updates. Current O…
Generative Cross-Entropy: A Strictly Proper Loss for Data-Efficient Classification
Qipeng Zhan, Zhuoping Zhou, Li Shen
Cross-entropy (CE) is the default training loss for supervised classification, but its sample efficiency is limited when labels are scarce. Existing remedies primarily act on the d…
Bi-Lipschitz Autoencoder With Injectivity Guarantee
Qipeng Zhan, Zhuoping Zhou, Zexuan Wang +2
Autoencoders are widely used for dimensionality reduction, based on the assumption that high-dimensional data lies on low-dimensional manifolds. Regularized autoencoders aim to pre…
Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach
Jiancong Xiao, Bojian Hou, Zhanliang Wang +4
One of the key technologies for the success of Large Language Models (LLMs) is preference alignment. However, a notable side effect of preference alignment is poor calibration: whi…
MentalChat16K: A Benchmark Dataset for Conversational Mental Health Assistance
Jia Xu, Tianyi Wei, Bojian Hou +7
We introduce MentalChat16K, an English benchmark dataset combining a synthetic mental health counseling dataset and a dataset of anonymized transcripts from interventions between B…