Scholar
Domenic Rosati
Google Scholar ID: 80aJAKYAAAAJ
Dalhousie University; Vector Institute
AI Safety
Trustworthy AI
Natural Language Generation
Representation Learning
Training Dynamics
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
636
H-index
12
i10-index
13
Publications
20
Co-authors
0
Publications
11 items
Removing Information Content Does Not Certify Tamper Resistance in Open-Weight Models
2026
Cited
0
Distribution-Specific Curvature Control with Finite-Sample Guarantees for Open-Weight Safety
2026
Cited
0
LLMs Underperform Graph-Based Parsers on Supervised Relation Extraction for Complex Graphs
2026
Cited
0
Limits of Convergence-Rate Control for Open-Weight Safety
2026
Cited
0
Dependency Parsing is More Parameter-Efficient with Normalization
2025
Cited
0
Content-aware rankings: a new approach to rankings in scholarship
2025
Cited
0
Improving Consistency in Large Language Models through Chain of Guidance
2025
Cited
0
Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities
2025
Cited
0
Load more
