Hannah Rose Kirk PRO
HannahRoseKirk
AI & ML interests
NLP; Active Learning; Adversarial Data Generation; Online Harms; Bias
Recent Activity
new activity
about 1 month ago
HannahRoseKirk/prism-alignment:What's this %?
updated
a dataset
9 months ago
HannahRoseKirk/prism-alignment
authored
a paper
9 months ago
Introducing v0.5 of the AI Safety Benchmark from MLCommons