Institution profile

National Research Institute

Academic institution
Research library1linked papers
Opportunities0open roles
Selected work

Representative Papers

Evaluating LLMs Robustness in Less Resourced Languages with Proxy Models

Jun 09, 2025

This work addresses the insufficient robustness of safety mechanisms in large language models (LLMs) for low-resource languages, exemplified by Polish. We propose a lightweight, efficient multi-granularity adversarial attack that computes token importance via a small surrogate model and applies character-level perturbations guided by importance-weighted selection—requiring minimal lexical or orthographic modifications. Experiments demonstrate that our attack substantially reduces safety response rates in Polish LLMs, revealing, for the first time, their heightened vulnerability to low-cost adversarial perturbations due to scarce safety-aligned training data. To support cross-lingual robustness evaluation and defense development, we publicly release the first Polish adversarial dataset and an extensible attack framework.

0 citationsRead paper
Recent publications

Latest Papers

Evaluating LLMs Robustness in Less Resourced Languages with Proxy Models

Jun 09, 2025

This work addresses the insufficient robustness of safety mechanisms in large language models (LLMs) for low-resource languages, exemplified by Polish. We propose a lightweight, efficient multi-granularity adversarial attack that computes token importance via a small surrogate model and applies character-level perturbations guided by importance-weighted selection—requiring minimal lexical or orthographic modifications. Experiments demonstrate that our attack substantially reduces safety response rates in Polish LLMs, revealing, for the first time, their heightened vulnerability to low-cost adversarial perturbations due to scarce safety-aligned training data. To support cross-lingual robustness evaluation and defense development, we publicly release the first Polish adversarial dataset and an extensible attack framework.

0 citationsRead paper