Search Results for author:
Found 8 papers, 3 papers with code
From Robustness to Improved Generalization and Calibration in Pre-trained Language Models
Enhancing generalization and uncertainty quantification in pre-trained language models (PLMs) is crucial for their effectiveness and reliability.
Out-of-Distribution Detection by Leveraging Between-Layer Transformation Smoothness
Effective out-of-distribution (OOD) detection is crucial for reliable machine learning models, yet most current methods are limited in practical use due to requirements like access to training data or intervention in training.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
+2
Parameter-Efficient Language Model Tuning with Active Learning in Low-Resource Settings
Pre-trained language models (PLMs) have ignited a surge in demand for effective fine-tuning techniques, particularly in low-resource domains and languages.
On Dataset Transferability in Active Learning for Transformers
We link the AL dataset transferability to the similarity of instances queried by the different PLMs and show that AL methods with similar acquisition sequences produce highly transferable datasets regardless of the models used.
You Are What You Talk About: Inducing Evaluative Topics for Personality Analysis
Expressing attitude or stance toward entities and concepts is an integral part of human behavior and personality.
Smooth Sailing: Improving Active Learning for Pre-trained Language Models with Representation Smoothness Analysis
Developed to alleviate prohibitive labeling costs, active learning (AL) methods aim to reduce label complexity in supervised learning.
Easy to Decide, Hard to Agree: Reducing Disagreements Between Saliency Methods
By connecting our findings to instance categories based on training dynamics, we show that the agreement of saliency method explanations is very low for easy-to-learn instances.
ALANNO: An Active Learning Annotation System for Mortals
Supervised machine learning has become the cornerstone of today's data-driven society, increasing the need for labeled data.
