Fairness and bias in NLP
Are you a researcher in the humanities or social sciences, working with text data? Are you currently (looking into) using natural language processing tools such as large language models? Then you may know that while AI tools are sometimes seen as “non-human thus objective”, this is a misconception. Just like humans, NLP tools can exhibit biases and unfair behavior or decision-making. This one-day workshop makes you aware of (un)fairness and bias in NLP, on a theoretical level and also in a hands-on way. After this course, you're all set to tackle your own data with AI in a more responsible way!
Praktische info:
Inschrijven?
- Voorwaarden: to have followed the course "Workshop Text Analysis using NLP for Researchers", or to have a basic notion of NLP
- Prijs: free
Make sure to bring a fully charged laptop with Python installed on it (version 3.9 or higher). Access to Google Colab (free or paying) is required, too.
Included in the workshop are: course material, coffee breaks.
Limited places available!
georganiseerd door:
Program
- Coffee and registration | 09.30 - 10.00
- Morning session | 10.00 - 12.00
- Introduction to large language models (LLMs)
- Background on fair machine learning (investigating cases such as COMPAS, Amazon, the ’toeslagenaffaire’)
- Intrinsic bias in language models: bias, hallucinations, toxicity, mitigation measures (e.g. RAG)
- Practical session on exploring biases in LLMs
- Lunch break | 12.00 - 13.00 (lunch not included)
- Afternoon session | 13.00 - 16.00
- Finetuning language models: different tasks, usage…
- Extrinsic biases of language models: metrics, mitigating extrinsic biases, implications
- Practical session on monitoring Twitter sentiment
- Legal issues: data usage, GDPR, AI act, institutional policies when performing research with LLMs
About the speakers and organizers
This course is organized by VAIA and the Antwerp Doctoral School of the University of Antwerp.
The workshop is taught by dr. Pieter Delobelle (KU Leuven) and Ewoenam Kwaku Tokpo (UAntwerp), who are experts in computer science, AI, and fairness and bias in language models.
Lesgevers / sprekers
Pieter Delobelle
Pieter Delobelle is momenteel AI-ingenieur bij Aleph Alpha, waar hij zich richt op inferentie, alignment en billijkheid van grote taalmodellen. Voorheen was hij postdoctoraal onderzoeker aan de KU Leuven met een specialisatie in bias en billijkheid in grote taalmodellen en ontwikkelde hij ook het state-of-the-art Nederlandse taalmodel RobBERT. Hij behaalde in 2018 een masterdiploma in de industriële wetenschappen aan de KU Leuven op de Technologiecampus Gent, België. Vervolgens behaalde hij een masterdiploma in kunstmatige intelligentie aan de KU Leuven en bleef hij daar voor een doctoraat in de computerwetenschappen onder professor Bettina Berendt en professor Luc De Raedt, dat hij in 2019 startte en in 2023 verdedigde, getiteld 'Towards fairer foundation models'. Zijn huidige onderzoek naar bias en billijkheid in grote taalmodellen leidde tot onderzoeksverblijven aan het Weizenbaum Instituut en de Bocconi Universiteit, evenals een stage bij Apple Inc.
Ewoenam Kwaku Tokpo
Ewoenam Kwaku Tokpo received a Master of Science in Computer Science from the University of Trento in 2019. He is currently a PhD student at the ADREM Research Lab in the Computer Science Department of the University of Antwerp. His research is focused on Fairness in Natural Language Models, where he explores issues of bias in natural language models and how these biases can be mitigated.
Gerelateerde opleidingen
AI voor Beginners - ChatGPT en co slim en verantwoord inzetten in je dagelijkse werk
Opleiding - Antwerpen - Thomas More Hogeschool, Syntra AB