Sotabase

Career

· PhD Student, University of Toronto2020–

Publications (13)

Universal Adversarial Triggers for Attacking and Analyzing NLP
Conference on Empirical Methods in Natural Language Processing · 2019
996
cited
Large Language Models Struggle to Learn Long-Tail Knowledge
International Conference on Machine Learning · 2022
561
cited
Deduplicating Training Data Mitigates Privacy Risks in Language Models
International Conference on Machine Learning · 2022
369
cited
Backdoor Attacks for In-Context Learning with Language Models
arXiv.org · 2023
111
cited
User Inference Attacks on Large Language Models
Conference on Empirical Methods in Natural Language Processing · 2023
37
cited
Universal Adversarial Triggers for NLP
arXiv.org · 2019
28
cited
Music Enhancement via Image Translation and Vocoding
IEEE International Conference on Acoustics, Speech, and Signal Processing · 2022
19
cited
Git-Theta: A Git Extension for Collaborative Development of Machine Learning Models
International Conference on Machine Learning · 2023
15
cited
AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution
International Conference on Learning Representations · 2024
13
cited
The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text
arXiv.org · 2025
11
cited
Position: The Most Expensive Part of an LLM should be its Training Data
International Conference on Machine Learning · 2025
7
cited
Efficient Model Development through Fine-tuning Transfer
Conference on Empirical Methods in Natural Language Processing · 2025
4
cited
Enhancing Training Data Attribution with Representational Optimization
arXiv.org · 2025
Sotabase
Nikhil Kandpal | Researcher Profile | Sotabase | Sotabase