16 citations · 20 across the 3 of their papers we have counts for
3 papers
Auditing Alignment Controllability in LLMs via Political Axes
Bartol Bućan, Nikola Sočec, Sarah Isufi +5
Political audits of large language models (LLMs) usually reduce each to one point on a political compass. But that resting point barely matters in deployment: a model must land som…
Mask-Mediator-Wrapper: A revised mediator-wrapper architecture for heterogeneous data source integration
Juraj Dončević, Krešimir Fertalj, Mario Brčić +1
This paper deals with the mediator-wrapper architecture. It is an important architectural pattern that enables a more flexible and modular architecture in opposition to monolithic…
Explainability in reinforcement learning: perspective and position
Agneza Krajna, Mario Brcic, Tomislav Lipic +1
Artificial intelligence (AI) has been embedded into many aspects of people's daily lives and it has become normal for people to have AI make decisions for them. Reinforcement learn…