Human Centered
Human-centered AI (HCAI) prioritizes human needs and values in the design, development, and deployment of AI systems. Current research focuses on improving AI explainability through methods like weight of evidence and counterfactual explanations, assessing AI's human-likeness in language and behavior using benchmarks informed by psycholinguistic principles and human feedback, and mitigating biases in AI models, particularly those stemming from Western-centric training data. This emphasis on human-centered design aims to enhance trust, transparency, and ultimately, the beneficial integration of AI into various applications, from healthcare and manufacturing to legal research and everyday tools.
Papers
On some Foundational Aspects of Human-Centered Artificial Intelligence
Luciano Serafini, Raul Barbosa, Jasmin Grosinger, Luca Iocchi, Christian Napoli, Salvatore Rinzivillo, Jacques Robin, Alessandro Saffiotti, Teresa Scantamburlo, Peter Schueller, Paolo Traverso, Javier Vazquez-Salceda
Explainability Is in the Mind of the Beholder: Establishing the Foundations of Explainable Artificial Intelligence
Kacper Sokol, Peter Flach