Niloofar Mireshghallah
12 papers · 2023–2025 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π Cross-Pollinator (15) π Conference Polyglot (7) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (19) π§ Keyword Pioneer
π
Triple Crown
β‘
Prolific Year
(6)
π
Century Club
(12)
β
The Questioner
Conferences
NAACL (4)
EMNLP (2)
ICLR (2)
ACL (1)
EACL (1)
ICML (1)
NIPS (1)
Top co-authors
Keywords
large language model
(5)
language model
(3)
text generation
(2)
training datum
(2)
instruction tuning
(1)
nearest neighbor retrieval
(1)
data privacy
(1)
adversarial attack
(1)
noise injection
(1)
copyright protection
(1)
prompt optimization
(1)
privacy leakage
(1)
data contamination
(1)
zero-shot detection
(1)
cloud computing
(1)
privacy-preserving training
(1)
synthetic dataset
(1)
model initialization
(1)
personally identifiable information
(1)
temporal adaptation
(1)
Papers
Differentially Private Learning Needs Better Model Initialization and Self-Distillation
NAACL 2025
Privacy Ripple Effects from Adding or Removing Personal Information in Language Model Training
ACL 2025
AI as Humanityβs Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text
ICLR 2025
Information-Guided Identification of Training Data Imprint in (Proprietary) Large Language Models
NAACL 2025
ALPACA AGAINST VICUNA: Using LLMs to Uncover Memorization of LLMs
NAACL 2025
LatticeGen: Hiding Generated Text in a Lattice for Privacy-Aware Large Language Model Generation on Cloud
NAACL 2024
WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models
NIPS 2024
Position: A Roadmap to Pluralistic Alignment
ICML 2024
Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory
ICLR 2024
Smaller Language Models are Better Zero-shot Machine-Generated Text Detectors
EACL 2024
CopyBench: Measuring Literal and Non-Literal Reproduction of Copyright-Protected Text in Language Model Generation
EMNLP 2024
Simple Temporal Adaptation to Changing Label Sets: Hashtag Prediction via Dense KNN
EMNLP 2023