Viewing profile — matus-pikuliak

I think this can be reduced to: whoever can send data to your LLMs can control all its resources. This includes all the tools and data sources involved.

That is absolutely not a reliable defense. Attackers can break these defenses. Some attacks are semantically meaningless, but they can nudge the model to produce harmful outputs. I…

I have done some research about AI-disinformation. This is a really complex topic, as disinformation or influence operations are complex phenomena that can have many different form…

In this particular case 50-50. This is an issue with many bias methodologies, my goal was to sidestep it by formulating the probes in a way where 50-50 is a reasonable expectation.…

To be honest, I am not sure where this bias comes from. It might be in the Web data, but it might also be overcorrection of the alignment tuning. They LLM providers are worried tha…

Let me shamelessly mention my GenderBench project focuses on evaluating gender biases in LLMs. Few of the probes are focused on hiring decisions as well, and indeed, women are ofte…

GenderBench is an open-source evaluation benchmark that measures gender biases in large language models. This is my attempt to decompose this pretty complex and difficult topic int…

Location: EU, Slovakia Remote: Preferably, willing to compromise for some offers Willing to relocate: For some offers Technologies: Python, LLMs, HuggingFace, PyTorch, typical ML s…

Location: EU, Slovakia Remote: Preferably yes Willing to relocate: For some offers Technologies: Python, LLMs, HuggingFace, PyTorch, typical ML stack (numpy, etc), Docker Résumé/CV…