Stefan Arnold
8 papers · 2023–2025 · 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Gold
🗺️
Taxonomy Completionist
(15)
Top co-authors
Research topics
Machine Learning
(6)
Artificial Intelligence
(5)
Natural Language Processing
(5)
Core AI
(5)
Resources & Methods
(5)
Application Areas
(4)
Security & Privacy
(3)
Differential Privacy
(3)
Deep Learning
(2)
Core Methods
(2)
Optimization & Theory
(2)
Computer Science
(1)
Applications
(1)
Learning Types
(1)
Models
(1)
Keywords
differential privacy
(5)
text privatization
(2)
language model
(2)
intrinsic dimension
(2)
bias mitigation
(1)
latent space
(1)
attention head
(1)
privacy leakage
(1)
encoder-decoder architecture
(1)
word embedding
(1)
latent structure
(1)
text paraphrasing
(1)
language model generation
(1)
activation steering
(1)
value vector
(1)
context sensitivity
(1)
representational similarity
(1)
probing classifier
(1)
sense embedding
(1)
sparse gating
(1)
Papers
Inspecting the Representation Manifold of Differentially-Private Text
NAACL 2025
Memorization in Language Models through the Lens of Intrinsic Dimension
ACL 2025
Steering Prepositional Phrases in Language Models: A Case of with-headed Adjectival and Adverbial Complements in Gemma-2
EMNLP 2025
Characterizing Stereotypical Bias from Privacy-preserving Pre-Training
ACL 2024
Routing in Sparsely-gated Language Models responds to Context
EMNLP 2024
Disentangling the Linguistic Competence of Privacy-Preserving BERT
EMNLP 2023
Driving Context into Text-to-Text Privatization
ACL 2023
Guiding Text-to-Text Privatization by Syntax
ACL 2023