Expected Harm: Rethinking Safety Evaluation of (Mis)Aligned LLMs
Paper
โข
2602.01600
โข
Published
โข
21
็ ๆฅท้
WangKaiLin
ยท
AI & ML interests
Hi, I'm an Independent Researcher ๐ฆ
Recent Activity
liked
a model
about 23 hours ago
nvidia/llama-embed-nemotron-8b
updated
a model
4 days ago
WangKaiLin/PipeOwl
published
a model
4 days ago
WangKaiLin/PipeOwl
Organizations
None yet
upvoted
a
paper
20 days ago