Fairness in LLMs
Can AI truly be fair in all languages? This presentation examines how biases in AI language models impact practice and presents strategies for measuring, mitigating, and developing multilingual AI systems.
Practical information:
Want to register?
- Prerequisites: Seminar for engineers or other technically trained professionals
- Price: 250
Georganiseerd door:
This presentation examines how biases in AI language models can lead to unfair outcomes in practical applications. We will explore methods for measuring and mitigating these biases, particularly across languages. We will also discuss broader security aspects and technical approaches for creating fairer and more responsible AI systems.
Teacher / speaker
Pieter Delobelle
Pieter Delobelle is currently an AI engineer at Aleph Alpha focussing on inference, alignment and fairness of large language models. Previously, he was a postdoctoral researcher at KU Leuven with a specialization in bias and fairness in large language models and he also developed the state-of-the-art Dutch language model RobBERT. He obtained a Masters in Engineering Technology from KU Leuven in 2018 at the Ghent Technology Campus, Belgium. Subsequently, he obtained an Advanced Masters in Artificial Intelligence from KU Leuven, and he stayed on for a Ph.D. in Computer Science under Professor Bettina Berendt and Professor Luc De Raedt, which he started in 2019 and defended in 2023, titled 'Towards fairer foundation models'. His current research on bias and fairness in large language models led to research visits at Weizenbaum Institute and Bocconi University, as well as an internship at Apple Inc.
Related courses
SAIAR Summer Studio: From latent to physical space
Zomerschool - Kortrijk - Howest Hogeschool, SAIARlab