arxiv:2503.00069
Karolina Stanczak
Karolina
AI & ML interests
None yet
Recent Activity
authored
a paper
about 13 hours ago
A Latent-Variable Model for Intrinsic Probing
authored
a paper
about 13 hours ago
Social Bias Probing: Fairness Benchmarking for Language Models
upvoted
a
paper
about 20 hours ago
Societal Alignment Frameworks Can Improve LLM Alignment
Organizations
