Marius Hobbhahn
4 papers · 2022–2025 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
๐
Conference Polyglot ยท Bronze
๐
Interdisciplinary Bridge ยท Bronze
๐บ๏ธ
Taxonomy Completionist
(10)
โ
The Questioner
Venues
Top co-authors
Research topics
Keywords
large language model
(2)
transfer learning
(1)
uncertainty quantification
(1)
question answering
(1)
instruction following
(1)
ai safety
(1)
synthetic data generation
(1)
false positive
(1)
dirichlet distribution
(1)
data efficiency
(1)
situational awareness
(1)
model self-awareness
(1)
behavioral testing
(1)
bayesian deep learning
(1)
predictive uncertainty
(1)
softmax output
(1)
model self-knowledge
(1)
linear probe
(1)
human-generated text
(1)
laplace bridge
(1)
Papers
Detecting Strategic Deception with Linear Probes
ICML 2025
Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs
NeurIPS 2024
Position: Will we run out of data? Limits of LLM scaling based on human-generated data
ICML 2024
Fast predictive uncertainty for classification with Bayesian deep networks
UAI 2022