544 citations · 586 across the 10 of their papers we have counts for
13 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…
AI-Assisted Unit Test Writing and Test-Driven Code Refactoring: A Case Study
Ema Smolic, Mario Brcic, Luka Hobor +1
Many software systems originate as prototypes or minimum viable products (MVPs), developed with an emphasis on delivery speed and responsiveness to changing requirements rather tha…
Bayesian Elicitation with LLMs: Model Size Helps, Extra "Reasoning" Doesn't Always
Luka Hobor, Mario Brcic, Mihael Kovac +1
Large language models (LLMs) have been proposed as alternatives to human experts for estimating unknown quantities with associated uncertainty, a process known as Bayesian elicitat…
The Memory Wars: AI Memory, Network Effects, and the Geopolitics of Cognitive Sovereignty
Mario Brcic
The advent of continuously learning Artificial Intelligence (AI) assistants marks a paradigm shift from episodic interactions to persistent, memory-driven relationships. This paper…
Comparative Analysis of Modern Machine Learning Models for Retail Sales Forecasting
Luka Hobor, Mario Brcic, Lidija Polutnik +1
Accurate demand forecasting is critical for brick-and-mortar retailers to optimize inventory management and minimize costs. This study evaluates statistical baselines, tree-based e…
Bidirectionalization For The Common People
Juraj Dončević, Mario Brčić, Danijel Mlinarić
This paper presents an innovative approach to applying bidirectional transformations (BX) in practice. To introduce BX to a wider audience of technologists, engineers, and research…
Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions
Luca Longo, Mario Brcic, Federico Cabitza +16
As systems based on opaque Artificial Intelligence (AI) continue to flourish in diverse real-world applications, understanding these black box models has become paramount. In respo…
Mask-Mediator-Wrapper architecture as a Data Mesh driver
Juraj Dončević, Krešimir Fertalj, Mario Brčić +1
The data mesh is a novel data management concept that emphasises the importance of a domain before technology. The concept is still in the early stages of development and many effo…
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…
Prismal view of ethics
Sarah Isufi, Kristijan Poje, Igor Vukobratovic +1
We shall have a hard look at ethics and try to extract insights in the form of abstract properties that might become tools. We want to connect ethics to games, talk about the perfo…
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…
Impossibility Results in AI: A Survey
Mario Brcic, Roman V. Yampolskiy
An impossibility theorem demonstrates that a particular problem or set of problems cannot be solved as described in the claim. Such theorems put limits on what is possible to do co…
AI safety: state of the field through quantitative lens
Mislav Juric, Agneza Sandic, Mario Brcic
Last decade has seen major improvements in the performance of artificial intelligence which has driven wide-spread applications. Unforeseen effects of such mass-adoption has put th…