Nikhil Kandpal
8 papers · 2019–2025 · 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
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(18)
🐣
Hot Topic Early Bird
Top co-authors
Research topics
Machine Learning
(6)
Artificial Intelligence
(5)
Core AI
(5)
Application Areas
(4)
Deep Learning
(3)
Natural Language Processing
(3)
Resources & Methods
(3)
Learning Types · Deep Learning
(2)
Learning Types · Machine Learning
(2)
Computer Science
(1)
Security & Privacy
(1)
Applications · Computer Science
(1)
Applications · Natural Language Processing
(1)
Models
(1)
Privacy
(1)
Keywords
large language model
(4)
membership inference
(2)
privacy attack
(2)
training data
(2)
language model
(2)
context attribution
(1)
adversarial attack
(1)
entity linking
(1)
adversarial trigger
(1)
model interpretability
(1)
retrieval augmentation
(1)
machine learning model
(1)
fact recall
(1)
transfer attack
(1)
leave-one-out error
(1)
model interpretation
(1)
knowledge memorization
(1)
parameter tracking
(1)
data attribution
(1)
question answering
(1)
Papers
AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution
ICLR 2025
Efficient Model Development through Fine-tuning Transfer
EMNLP 2025
Position: The Most Expensive Part of an LLM *should* be its Training Data
ICML 2025
User Inference Attacks on Large Language Models
EMNLP 2024
Git-Theta: A Git Extension for Collaborative Development of Machine Learning Models
ICML 2023
Large Language Models Struggle to Learn Long-Tail Knowledge
ICML 2023
Deduplicating Training Data Mitigates Privacy Risks in Language Models
ICML 2022
Universal Adversarial Triggers for Attacking and Analyzing NLP
EMNLP 2019