NASK National Research Institute

university

https://science.nask.pl/en

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

WojciechKusa authored a paper 17 days ago

Multilingual Refusal Alignment for Safer Large Language Models

WojciechKusa authored a paper 17 days ago

Reassessing High-Performing LLMs on Polish Medical Exams: True Competence or Bias-Driven Performance?

WojciechKusa updated a collection 17 days ago

Multilingual Refusal Alignment

View all activity

authored 2 papers 17 days ago

Multilingual Refusal Alignment for Safer Large Language Models

Paper • 2606.07535 • Published Apr 24

Reassessing High-Performing LLMs on Polish Medical Exams: True Competence or Bias-Driven Performance?

Paper • 2606.12250 • Published 19 days ago

updated a collection 17 days ago

Multilingual Refusal Alignment

RefusEU dataset from "Multilingual Refusal Alignment for Safer Large Language Models" by A. Krasnodębska, W. Kusa, A. Lipani (ACL Findings 2026). • 3 items • Updated 17 days ago

updated a Space 28 days ago

RefusEU

Presenting results from RefusEU dataset

authored a paper about 1 month ago

Monitoring the Internal Monologue: Probe Trajectories Reveal Reasoning Dynamics

Paper • 2605.18549 • Published May 18 • 2

submitted a paper to Daily Papers about 1 month ago

Monitoring the Internal Monologue: Probe Trajectories Reveal Reasoning Dynamics

Paper • 2605.18549 • Published May 18 • 2

aleksandrakrasno

published a dataset about 2 months ago

NASK-PIB/RefusEU

Viewer • Updated May 8 • 86.1k • 50

updated a collection about 2 months ago

Multilingual Refusal Alignment

RefusEU dataset from "Multilingual Refusal Alignment for Safer Large Language Models" by A. Krasnodębska, W. Kusa, A. Lipani (ACL Findings 2026). • 3 items • Updated 17 days ago

published a Space about 2 months ago

RefusEU

Presenting results from RefusEU dataset

updated a dataset about 2 months ago

NASK-PIB/RefusEU

Viewer • Updated May 8 • 86.1k • 50

aleksandrakrasno

updated a dataset 3 months ago

NASK-PIB/RefusEU

Viewer • Updated May 8 • 86.1k • 50

aleksandrakrasno

updated a collection 3 months ago

Multilingual Refusal Alignment

RefusEU dataset from "Multilingual Refusal Alignment for Safer Large Language Models" by A. Krasnodębska, W. Kusa, A. Lipani (ACL Findings 2026). • 3 items • Updated 17 days ago

authored a paper 4 months ago

Conditioned Activation Transport for T2I Safety Steering

Paper • 2603.03163 • Published Mar 3 • 1

updated a collection 4 months ago

LLaVA-PLLuM

Polish Vision-Language Model based on PLLuM and LLaVA frameworks • 6 items • Updated 3 days ago

submitted a paper to Daily Papers 4 months ago

Conditioned Activation Transport for T2I Safety Steering

Paper • 2603.03163 • Published Mar 3 • 1

published a dataset 4 months ago

NASK-PIB/SafeSteerDataset

Viewer • Updated Mar 4 • 2.3k • 59 • 2

updated a dataset 4 months ago

NASK-PIB/SafeSteerDataset

Viewer • Updated Mar 4 • 2.3k • 59 • 2

updated a Space 4 months ago

LLaVA PLLuM

LLaVA-PLLuM: a Polish Vision-Language Model

published a dataset 4 months ago

NASK-PIB/MMBench_V11_PL

Viewer • Updated Mar 2 • 9.75k • 24

updated a dataset 4 months ago

NASK-PIB/MMBench_V11_PL

Viewer • Updated Mar 2 • 9.75k • 24