research
∙
08/02/2023
XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models
Without proper safeguards, large language models will readily follow mal...
share
research
∙
10/14/2022
The State of Profanity Obfuscation in Natural Language Processing
Work on hate speech has made the consideration of rude and harmful examp...
research
∙
03/17/2022
Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists
Natural Language Processing (NLP) models risk overfitting to specific te...
research
∙
04/08/2020
