Search Results for author:
Found 9 papers, 3 papers with code
Thermometer: Towards Universal Calibration for Large Language Models
Addressing these challenges, we propose THERMOMETER, a calibration approach tailored to LLMs.
Improved Evidential Deep Learning via a Mixture of Dirichlet Distributions
This paper explores a modern predictive uncertainty estimation approach, called evidential deep learning (EDL), in which a single neural network model is trained to learn a meta distribution over the predictive distribution by minimizing a specific objective function.
Reliable Gradient-free and Likelihood-free Prompt Tuning
Due to privacy or commercial constraints, large pre-trained language models (PLMs) are often offered as black-box APIs.
Group Fairness with Uncertainty in Sensitive Attributes
To overcome this limitation, we propose a bootstrap-based algorithm that achieves the target level of fairness despite the uncertainty in sensitive attributes.
Post-hoc Uncertainty Learning using a Dirichlet Meta-Model
It is known that neural networks have the problem of being over-confident when directly using the output label distribution to generate uncertainty measures.
Batch Active Learning from the Perspective of Sparse Approximation
Active learning enables efficient model training by leveraging interactions between machine learning agents and human annotators.
On Balancing Bias and Variance in Unsupervised Multi-Source-Free Domain Adaptation
Due to privacy, storage, and other constraints, there is a growing need for unsupervised domain adaptation techniques in machine learning that do not require access to the data used to train a collection of source models.
Source-Free Domain Adaptation
Unsupervised Domain Adaptation
SABAL: Sparse Approximation-based Batch Active Learning
We propose a novel and general framework (i. e., SABAL) that formulates batch active learning as a sparse approximation problem.
Dimensionality Reduction via Diffusion Map Improved with Supervised Linear Projection
When performing classification tasks, raw high dimensional features often contain redundant information, and lead to increased computational complexity and overfitting.
