arxiv:2411.19240
Alina Leidinger
alinaleidinger
ยท
AI & ML interests
None yet
Recent Activity
authored
a paper
4 days ago
Probing LLMs for Joint Encoding of Linguistic Categories
authored
a paper
4 days ago
How far can bias go? -- Tracing bias from pretraining data to alignment
authored
a paper
about 1 month ago
CIVICS: Building a Dataset for Examining Culturally-Informed Values in
Large Language Models
Organizations
models
None public yet
datasets
None public yet