Search | Research Portal

Chosen filters:

explainability

Chosen filters:

explainability

1 - 6 of 6 results

Sorteren op

Conversational & Transparent Explainability in Fake Media Detection Ghent University

Glenn Van Wallendael

Department of Electronics and information systems

The rise of AI-generated media has made creating fake content easier and more realistic, posing societal risks such as disinformation, fake evidence, and fraud. While detection methods for fake media have advanced, they lack interpretability, making them inaccessible and untrustworthy for non-expert users, and limiting their adoption in critical domains. Moreover, most research focuses on detecting fake images, leaving video and emerging 3D ...

Enhancing Digital Engagement and Explainability of AI-Driven Stress Management KU Leuven

Vero Vanden Abeele

Human-Computer Interaction (HCI)

This PhD research will investigate how digital engagement with AI-based technologies can be enhanced in the context of stress recovery and adaptive coping mechanisms. It aims to deepen our understanding of how to integrate smart, motivational design techniques to promote adherence to interventions and improve overall well-being.

An agentic codified framework for lower hallucination and better explainability in Legal question answering. University of Antwerp

Walter Daelemans

Business and Law, Centre for Computational Linguistics, Psycholinguistics and Sociolinguistics (CLiPS)

In this project, we aim to overcome hallucinations in LLM legal assistants by developing an agentic codified solution for legal question-answering (QA), which incorporates rule-based and (programming) code-based representations of law, as well as distributed reasoning and verification. The trustworthy legal research assistant will transform the daily search routine of legal professionals by speeding up the process and enhancing their efficiency. ...

On the Relationship Between Proofs and Explanations KU Leuven

Bart Bogaerts

Declarative Languages and Artificial Intelligence (DTAI)

The ultimate dream of declarative problem solving is that one should only specify their problems, in an human-understandable way and that a computer can then automatically solve them. In this project, we are concerned with two issues related to solvers that actually do this for us. The first is explainability: how can such a tool explain its decisions to the user who specified the problem in the first place. The second is ...

ProToX: From Proofs to Explanations (and Back Again) KU Leuven

Bart Bogaerts

Declarative Languages and Artificial Intelligence (DTAI)

The ultimate dream of declarative problem solving is that one should only specify their problems, in an human-understandable way and that a computer can then automatically solve them.
In this project, we are concerned with two issues related to solvers that actually do this for us.
The first is explainability: how can such a tool explain its decisions to the user who specified the problem in the first place.
The second is ...

Sabbatical Celine Vens: Advanced machine learninig methods in healthcare KU Leuven

Celine Vens

Public Health and Primary Care, Kulak Kortrijk Campus

The advent of deep learning methods has revolutionized the field of machine learning and its practical applications. Also in the domain of healthcare, deep learning has led to many breaktroughs, for example in computerized diagnostics. Although most of the initial successes have been achieved in the context of medical imaging, we are now seeing many applications of deep learning with other sources of medical data, such as electronic health ...