About this project

Le projet UnBias AI s’intéresse aux biais potentiels présents dans les modèles d’intelligence artificielle, notamment dans les contextes corporatifs et décisionnels.
Ces biais peuvent se manifester de plusieurs manières :
Donner plus de poids aux données récentes,
Renforcer certaines perspectives ou narratifs existants,
Occulter des informations pertinentes mais moins représentées.

L’objectif est de détecter, analyser et atténuer ces biais afin de construire des systèmes d’IA plus transparents, équitables et fiables, contribuant ainsi à une prise de décision plus juste et responsable.

Ce projet repose sur la collaboration entre DTSC et l’Université d’Anvers (UAntwerpen), alliant expertise en cybersécurité, en IA et en recherche académique.

💻 GitHub – Codes & expérimentations
📑 Articles & publications associés

Discover the team behind "UnBias AI"

Shreya Bhattacharya
Shreya BhattacharyaSenior Data Scientist
PhD in Applied Statistics – Postdoc Researcher in Solar Physics – Expertise in Advanced Statistical Analysis & Machine Learning at Université Libre de Bruxelles, ULB
Vincent Hagenow
Vincent HagenowDigital Text Analysis Student
BA in Classical Philology | Master of Digital Text Analysis, Computer Programming
Marco Di Gennaro
Marco Di GennaroCTO
Orcid
PhD in Physics in Liège University | Postdoc Bale University | +15 years of R&D
Published On: 15 November 2025Categories: Tags:

Related projects

View all projects

  • EnergyAgent

    EnergyAgent is an LLM-powered conversational assistant for household energy monitoring and efficiency. It enables natural-language queries over smart-meter data and provides strictly factual responses derived from recorded consumption. User questions are translated into explicit calculation steps processed by an analytics engine, ensuring numerical accuracy. The system then converts these results into clear, actionable insights to help users better understand and optimize their energy usage.

  • Energy – PINN Transformers

    This project leverages Physics-Informed Neural Networks (PINNs) to model and forecast the thermal performance of power transformers in the Belgian transmission network. By combining physical thermal equations with historical operational and environmental data, the approach enables accurate temperature estimation, early detection of overheating risks, and supports data-driven predictive maintenance strategies.

  • AI for Corporate

    This project represents a strategic shift from single, general-purpose AI models to an ensemble ecosystem purpose-built for the legal domain. Unlike conventional models that struggle with contractual complexity, this architecture mirrors a legal professional’s reasoning: prioritizing precision, intent comprehension, and rigorous source validation.

  • EnergyAgent

    EnergyAgent is an LLM-powered conversational assistant for household energy monitoring and efficiency. It enables natural-language queries over smart-meter data and provides strictly factual responses derived from recorded consumption. User questions are translated into explicit calculation steps processed by an analytics engine, ensuring numerical accuracy. The system then converts these results into clear, actionable insights to help users better understand and optimize their energy usage.

  • Energy – PINN Transformers

    This project leverages Physics-Informed Neural Networks (PINNs) to model and forecast the thermal performance of power transformers in the Belgian transmission network. By combining physical thermal equations with historical operational and environmental data, the approach enables accurate temperature estimation, early detection of overheating risks, and supports data-driven predictive maintenance strategies.