4 papers
Is Refusal Direction Universal across Low-Resourced Languages?
Anastasiia Ivanova
Refusal directions have been shown to transfer cross-lingually with near-perfect effectiveness across safety-aligned languages (Wang et al., 2025), reportedly regardless of resourc…
AmbiK: Dataset of Ambiguous Tasks in Kitchen Environment
Anastasiia Ivanova, Eva Bakaeva, Zoya Volovikova +2
As a part of an embodied agent, Large Language Models (LLMs) are typically used for behavior planning given natural language instructions from the user. However, dealing with ambig…
Voices of Freelance Professional Writers on AI: Limitations, Expectations, and Fears
Anastasiia Ivanova, Natalia Fedorova, Sergei Tilga +1
The rapid development of AI-driven tools, particularly large language models (LLMs), is reshaping professional writing. Still, key aspects of their adoption such as language suppor…
RuBia: A Russian Language Bias Detection Dataset
Veronika Grigoreva, Anastasiia Ivanova, Ilseyar Alimova +1
Warning: this work contains upsetting or disturbing content. Large language models (LLMs) tend to learn the social and cultural biases present in the raw pre-training data. To test…