FatemehSadat Mireshghallah
13 papers · 2021–2024 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (29) π Conference Polyglot (7) π Renaissance Researcher (5) π Interdisciplinary Bridge π§ Keyword Pioneer
π
Conference Polyglot
(7)
π
Renaissance Researcher
(5)
π
Keyword Champion
(3)
π
Century Club
(13)
ποΈ
Keyword Collector
(58)
β‘
Prolific Year
(5)
Conferences
EMNLP (4)
ACL (3)
NAACL (2)
CONLL (1)
EACL (1)
ICLR (1)
NIPS (1)
Top co-authors
Research topics
Keywords
language model
(4)
differential privacy
(4)
text generation
(3)
privacy risk
(3)
membership inference
(3)
energy-based model
(3)
metropolis-hastings sampling
(3)
membership inference attack
(2)
controllable generation
(2)
natural language processing
(1)
masked language model
(1)
semantic parsing
(1)
language modeling
(1)
task-oriented dialogue
(1)
sentiment analysis
(1)
false positive rate
(1)
domain adaptation
(1)
model pruning
(1)
markov chain monte carlo
(1)
style transfer
(1)
Papers
Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation
ICLR 2024
Privacy-Preserving Domain Adaptation of Semantic Parsers
ACL 2023
Membership Inference Attacks against Language Models via Neighbourhood Comparison
ACL 2023
A Block Metropolis-Hastings Sampler for Controllable Energy-based Text Generation
EMNLP 2023
A Block Metropolis-Hastings Sampler for Controllable Energy-based Text Generation
CONLL 2023
Privacy-Preserving Natural Language Processing
EACL 2023
Differentially Private Model Compression
NIPS 2022
Mix and Match: Learning-free Controllable Text Generationusing Energy Language Models
ACL 2022
An Empirical Analysis of Memorization in Fine-tuned Autoregressive Language Models
EMNLP 2022
Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks
EMNLP 2022
UserIdentifier: Implicit User Representations for Simple and Effective Personalized Sentiment Analysis
NAACL 2022
Privacy Regularization: Joint Privacy-Utility Optimization in LanguageModels
NAACL 2021
Style Pooling: Automatic Text Style Obfuscation for Improved Classification Fairness
EMNLP 2021