Maria Marina's picture

2 18

Maria Marina

zlatamaria

·

marialysyuk

AI & ML interests

None yet

Recent Activity

upvoted a paper 2 days ago

The Rogue Scalpel: Activation Steering Compromises LLM Safety

upvoted a paper 2 days ago

When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA

upvoted a paper 13 days ago

OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features

View all activity

Organizations

commented 3 papers 4 months ago

Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA

Paper • 2505.21115 • Published May 27 • 139 •

Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA

Paper • 2505.21115 • Published May 27 • 139 •

Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA

Paper • 2505.21115 • Published May 27 • 139 •

commented a paper 8 months ago

How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM?

Paper • 2502.14502 • Published Feb 20 • 91 •