Karolina Seweryn
5 papers · 2025–2026 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(2)
🌉
Interdisciplinary Bridge
🗺️
Taxonomy Completionist
(14)
🐝
Cross-Pollinator
(15)
⭐
Rising Star
(5)
Conferences
EACL (3)
ACL (1)
EMNLP (1)
Top co-authors
Keywords
polish language
(2)
safety evaluation
(2)
language model
(2)
multilingual nlp
(2)
text classification
(1)
preference learning
(1)
factual accuracy
(1)
cross-lingual transfer
(1)
preference optimization
(1)
toxicity detection
(1)
bias detection
(1)
language model alignment
(1)
model safety
(1)
responsible ai
(1)
low-resource language
(1)
vision-language model
(1)
alignment method
(1)
multimodal model
(1)
human annotation
(1)
multilingual natural language processing
(1)
Papers
Safety of Large Language Models Beyond English: A Systematic Literature Review of Risks, Biases, and Safeguards
EACL 2026
Rethinking the Evaluation of Alignment Methods: Insights into Diversity, Generalisation, and Safety
EACL 2026
Annotation-Efficient Vision-Language Model Adaptation to the Polish Language Using the LLaVA Framework
EACL 2026
PL-Guard: Benchmarking Language Model Safety for Polish
ACL 2025
PLLuM-Align: Polish Preference Dataset for Large Language Model Alignment
EMNLP 2025