Stefano Teso Senior Assistant Professor at CIMeC and DISI, University of Trento There is an increasing need of Artificial Intelligence (AI) and Machine Learning (ML) models that can reliably output predictions matching our expectations. Models learned from data should comply with specifications of desirable behavior supplied or elicited from humans and avoid overconfidence, i.e., being

Luuk de Jong Master student at Universiteit Leiden This project investigates the integration of a reject option in machine learning models to enhance reliability and explainability. By rejecting uncertain predictions, we can mitigate risks associated with low-confidence decisions, meaning the model will be more reliable. The core contribution of this work is the development and

Patrick Lang B.Sc. at N4 N4, a leading provider of procurement platforms in the automotive sector, is facing the challenge of making its catalogs for car parts (N4Parts) more user-friendly. These catalogs are used by customers both to purchase parts and to obtain information, such as installation instructions and maintenance intervals. The use of such

Jeff Clark Research Fellow at the University of Bristol With the widespread deployment of AI systems, it becomes increasingly important that users are equipped to scrutinise these models and their outputs. This is particular true for applications in high stakes domains such as healthcare. We propose to conduct research in the context of explainable AI,

Dan Saattrup Nielsen PhD student at Alexandra Instituttet Presentation on the benchmarking of LLMs, with a specific application to the Northern European languages. The challenges of evaluating generative language models, the different ways in which this can be done, and the current status within the Northern European language will be presented. This is followed by

Nadeem Qazi Senior Lecturer in AI machine learning at University of East London,UK Alzheimer’s disease (AD) is becoming more common, emphasizing the need for early detection and prediction to improve patient outcomes. Current diagnostic methods are often too late, missing the opportunity for early intervention. This research seeks to develop advanced explainable AI models that