Sophie Xhonneux
Scholar

Sophie Xhonneux

Google Scholar ID: 9TQM9k4AAAAJ
PhD Student at Mila & University of Montréal
machine learninggraphsrepresentation learninggenerative models
Google Scholar↗
Citations & Impact
All-time
Citations
1,597
 
H-index
11
 
i10-index
11
 
Publications
20
 
Co-authors
14
list available
Contact
No contact links provided.
Publications
6 items
Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs
2025
Cited
0
LLM-Safety Evaluations Lack Robustness
2025
Cited
0
A generative approach to LLM harmfulness detection with special red flag tokens
2025
Cited
0
Adversarial Alignment for LLMs Requires Simpler, Reproducible, and More Measurable Objectives
2025
Cited
0
Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models
arXiv.org · 2024
Cited
2
Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space
Neural Information Processing Systems · 2024
Cited
36
Resume (English only)
Co-authors
14 total
Jian Tang (唐建）
Jian Tang (唐建）
Associate Professor, Mila-Quebec AI Institute, HEC Montréal, Canada CIFAR AI Chair
Zhaocheng Zhu
Zhaocheng Zhu
Research Scientist, NVIDIA
Leo Schwinn
Leo Schwinn
Technical University of Munich
Gauthier Gidel
Gauthier Gidel
Associate professor at University of Montréal (DIRO), Core Member of Mila, Canada CIFAR AI Chair
Co-author 5
Co-author 5
Stephan Günnemann
Stephan Günnemann
Professor of Computer Science, Technical University of Munich
Zuobai Zhang
Zuobai Zhang
Quebec AI Institute (Mila)
Jun-Kun Chen
Jun-Kun Chen
Ph.D. Candidate of Computer Science, University of Illinois Urbana-Champaign