RefusEU dataset from "Multilingual Refusal Alignment for Safer Large Language Models" by A. Krasnodębska, W. Kusa, A. Lipani (ACL Findings 2026).
AI & ML interests
None defined yet.
Recent Activity
View all activity
models 5
NASK-PIB/LLaVA-Bielik-11b-v2.6-instruct
Image-Text-to-Text • 12B • Updated • 66 • 2
NASK-PIB/LLaVA-PLLuM-12b-nc-instruct
Image-Text-to-Text • 13B • Updated • 55 • 1
NASK-PIB/LLaVA-PLLuM-12b-nc-instruct-250715
Image-Text-to-Text • 13B • Updated • 10 • 2
NASK-PIB/HerBERT-PL-Guard
Text Classification • 0.1B • Updated • 129 • 3
NASK-PIB/BANonymizer-PL
0.4B • Updated • 80 • 2
datasets 7
NASK-PIB/RefusEU
Viewer • Updated • 86.1k • 50
NASK-PIB/SafeSteerDataset
Viewer • Updated • 2.3k • 64 • 2
NASK-PIB/MMBench_V11_PL
Viewer • Updated • 9.75k • 35
NASK-PIB/PLLuM-Align
Preview • Updated • 80 • 3
NASK-PIB/PL-Guard
Viewer • Updated • 1.8k • 56 • 1
NASK-PIB/non-harmful_prompts_sample
Viewer • Updated • 484 • 12
NASK-PIB/harmful_prompts_sample
Viewer • Updated • 428 • 12 • 1