Scholar
Geraldin Nanfack
Google Scholar ID: 0_jhp0EAAAAJ
Concordia University
Trustworthy AI
Machine Learning
Deep Learning
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
390
H-index
9
i10-index
9
Publications
19
Co-authors
24
list available
Contact
No contact links provided.
Publications
2 items
Circuit Discovery Helps Detect LLM Jailbreaking: A Mechanistic Interpretability Study
2026
Cited
0
Efficient Refusal Ablation in LLM through Optimal Transport
2026
Cited
0
Resume (English only)
Co-authors
24 total
Frénay Benoît
Faculty of Computer Science, Université de Namur
Co-author 2
Eugene Belilovsky
Associate Professor, Concordia University and Mila Quebec AI Institute
Hendrik Blockeel
Department of Computer Science, KU Leuven
Siegfried Nijssen
Professor at KU Leuven; guest professor at UCLouvain
Laurens Devos
KU Leuven
Co-author 7
Christophe De Vleeschouwer
Professor, ICTEAM, EPL, Université catholique de Louvain
