trustworthy-ai

Seminar on trustworthy artificial intelligence from a sociotechnical perspective, covering high-impact decisions, social networks, and human-AI collaboration.

Round table on the role of artificial intelligence in science and health, with a focus on AI4Health, responsible research, and trustworthy deployment.

Masterclass on algorithmic discrimination, bias, and trustworthy AI in public-sector decision-making with a gender perspective.

Outreach talk introducing high-school students to artificial intelligence, its opportunities, and its societal risks.

Outreach talk on AI and science for more than 700 high-school students, focused on the risks of AI systems beyond large language models.

This work evaluates how LLMs handle mental health crises, introducing a unified taxonomy, benchmark dataset, and expert-based evaluation protocol — revealing both support capabilities and significant safety risks.

Seminar on algorithmic bias, discrimination risks, and fairness-aware AI systems in high-stakes decision-making contexts.

PhD thesis proposing a sociotechnical framework for Trustworthy AI, with contributions in fairness (FairShap), structural disparity in networks (ERG), human–AI complementarity for matching, and AI governance in labor law.

CoMatch is a collaborative matching system that combines human decisions with algorithmic decisions to outperform humans or algorithms alone.

We define three metrics of the group information power (social capital) in a network based on effective resistance (spectral graph theory). We propose also three metrics of social capital unfairness (structural group unfairness) and a heuristic to mitigate it.