PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models
Paper • 2606.09697 • Published • 7 •
4
Gianluca Barmina
giannor
AI & ML interests
None yet
Recent Activity
liked a model 13 days ago
danish-foundation-models/DFM-Mimir submitted a paper 16 days ago
DFM Mimir v1: An Open HRM Delivering Frontier Performance at 1B Parameters Using Only Permissible Post-Training Data authored a paper 18 days ago
DFM Mimir v1: An Open HRM Delivering Frontier Performance at 1B Parameters Using Only Permissible Post-Training DataOrganizations
commented a
paper 3 months ago
Update README.md
#1 opened 3 months ago
by giannor
Added confidence interval calculation
1
#6 opened 9 months ago
by 
giannor
Updated model name
#4 opened 9 months ago
by giannor
Updated table evaluation results
1
#3 opened 10 months ago
by giannor
Update README with evaluation results
3
#2 opened 10 months ago
by giannor
Update README with evaluation results
3
#2 opened 10 months ago
by giannor