boczkakaroly/hungarian-riddles-benchmark
Viewer
•
Updated
•
100
•
68
Károly Boczka
boczkakaroly
·
AI & ML interests
Multilingual AI evaluator & data analyst (HU/EN/SR/HR, RU/UA). I build evaluation benchmarks, cultural bias tests, and prompt-engineering analyses. Focused on transparent, reproducible, multilingual model quality.
Recent Activity
updated
a dataset
3 days ago
boczkakaroly/hungarian-riddles-benchmark
updated
a dataset
3 days ago
boczkakaroly/trilingual-cultural-bias-redteaming-benchmark
liked
a Space
about 1 month ago
OpenEvals/evaluation-guidebook
Organizations
None yet