research
∙
06/27/2023
On the Universal Adversarial Perturbations for Efficient Data-free Adversarial Detection
Detecting adversarial samples that are carefully crafted to fool the mod...
share
research
∙
06/27/2023
DSRM: Boost Textual Adversarial Training with Distribution Shift Risk Minimization
Adversarial training is one of the best-performing methods in improving ...
research
∙
05/04/2023
CausalAPM: Generalizable Literal Disentanglement for NLU Debiasing
Dataset bias, i.e., the over-reliance on dataset-specific literal heuris...
research
∙
10/14/2022
Kernel-Whitening: Overcome Dataset Bias with Isotropic Sentence Embedding
Dataset bias has attracted increasing attention recently for its detrime...
research
∙
04/09/2022
MINER: Improving Out-of-Vocabulary Named Entity Recognition from an Information Theoretic Perspective
NER model has achieved promising performance on standard NER benchmarks....
research
∙
02/16/2022
Decorrelate Irrelevant, Purify Relevant: Overcome Textual Spurious Correlations from a Feature Perspective
Natural language understanding (NLU) models tend to rely on spurious cor...
research
∙
07/08/2021