arxiv:2406.11704
Leon Derczynski
leondz
AI & ML interests
llm security, datasets, efficiency, abusive language detection, temporal information extraction, social media processing, danish
Recent Activity
upvoted
a
paper
about 2 months ago
garak: A Framework for Security Probing Large Language Models
updated
a model
7 months ago
garak-llm/attackgeneration-toxicity_gpt2
new activity
7 months ago
leondz/artopttox350m:Adding `safetensors` variant of this model