Christos Emmanouilidis receives funding for collaborative EU research project on making AI explainable, transparent and accountable

Associate Professor Christos Emmanouilidis has received funding for a major new Collaborative Horizon Europe research project on the next generation of transparent, robust, and auditable agentic AI. The project is titled ‘AIXPERT: An agentic, multi-layer, GenAI-powered backbone to make an AI system explainable, accountable, and transparent’ and is set to start on the 1^st of June 2025.

AIXPERT envisions a future where AI systems are explainable, transparent, accountable, and robust, fostering trust in human-machine interactions. The AIXPERT solutions will measure the efficiency and accuracy of AI systems and will also provide contextual explanations, offering insights into the data and models used to generate outcomes. The integration of Knowledge Graphs (KGs) with AI agents will link the data and the actions taken by AI agents. Reinforcement Learning from Human Feedback (RLHF) will enable AI to learn and adapt based on real-time user interactions. The dynamic creation and configuration of AI agents will allow users to customise and deploy AI, primarily powered by Large Language Models (LLMs). AIXPERT will leverage human-centred design principles, incorporating participatory design and usability studies.

UG’s role in the project

The project is co-ordinated by ATHENA Research and Innovation Centre, Greece. The interdisciplinary consortium consists of 17 partners from 10 countries. This is a 7.5 million euro project, with about 750k euros funding for the University of Groningen. UG's team is headed by Emmanouilidis, who is an associate professsor at the Faculty of Economics and Business. His team will lead the development of an auditing and evaluation framework, working closely with ATHENA, as well as the Vector Institute in Canada in this line of research. The team will aim towards the development of social equity-centred and ethically aligned models, and will primarily contribute to the Integration of KGs and LLMs for enhanced decision-making, and the overall cross-domain validation and societal impact assessment of AI systems, demonstrated in the domains of clinical decision-support systems in healthcare, HRM and hiring processes, manufacturing production processes, educational robotics and AI-assisted music generation.

The team from the UG will particularly support innovative AI applications on production and maintenance processes at Philips Drachten. The project will involve two new PhD researchers, one working on Auditing and Evaluating AI Systems, and one on Integrating Knowledge Graphs with LLMs in Agentic AI workflows. The doctoral researchers will also be supported by ATHENA Research and Innovation Centre regarding the development of LLM-based agentic AI and will collaborate with the Vector Institute regarding the auditing and evaluation of AI systems.

For more information, please contact Christos Emmanouilidis.