Scholar
Niels Warncke
Google Scholar ID: K8lmHy0AAAAJ
Center on Longterm-Risk
Machine Learning
LLMs
AI safety
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
84
H-index
2
i10-index
1
Publications
4
Co-authors
0
Contact
No contact links provided.
Publications
4 items
Value Leakage: An LLM's Answers Are Silently Shaped by Its Own Values
2026
Cited
0
Inoculation Adapters: Improved Selective Generalization of Capabilities with Fewer Surprising Backdoors
2026
Cited
0
Inoculation Prompting: Eliciting traits from LLMs during training can suppress them at test-time
2025
Cited
0
Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs
2025
Cited
0
Resume (English only)
Co-authors
0 total
Co-authors: 0 (list not available)
