Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale
Paper
•
2211.03759
•
Published
safety-by-imitation
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
safety-by-imitation's activity
vinid
authored
6
papers
7 months ago
Contrastive Language-Image Pre-training for the Italian Language
Paper
•
2108.08688
•
Published
•
2
XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models
Paper
•
2308.01263
•
Published
Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions
Paper
•
2309.07875
•
Published
When and why vision-language models behave like bags-of-words, and what to do about it?
Paper
•
2210.01936
•
Published
TextGrad: Automatic "Differentiation" via Text
Paper
•
2406.07496
•
Published
•
28
Paul
authored
a
paper
9 months ago
g8a9
authored
4
papers
about 1 year ago
XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models
Paper
•
2308.01263
•
Published
Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions
Paper
•
2309.07875
•
Published
Explaining Speech Classification Models via Word-Level Audio Segments and Paralinguistic Features
Paper
•
2309.07733
•
Published
A Tale of Pronouns: Interpretability Informs Gender Bias Mitigation for Fairer Instruction-Tuned Machine Translation
Paper
•
2310.12127
•
Published
•
1
g8a9
authored
3
papers
over 1 year ago