Nikhil Kandpal

22 papers A* 6Misc 1Journal 13Unranked 2

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	IH-Challenge: A Training Dataset to Improve Instruction Hierarchy on Frontier LLMs. CoRR Chuan Guo, Juan Felipe Ceron Uribe, Sicheng Zhu, Christopher A. Choquette-Choo, Stephanie Lin, Nikhil Kandpal, Milad Nasr, Rai, Sam Toyer, Miles Wang, Yaodong Yu, Alex Beutel, Kai Xiao
2025	A*	`conf`	AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution. ICLR Fengyuan Liu, Nikhil Kandpal, Colin Raffel
2025	A*	`conf`	Efficient Model Development through Fine-tuning Transfer. EMNLP Pin-Jie Lin, Rishab Balasubramanian, Fengyuan Liu, Nikhil Kandpal, Tu Vu
2025	J	`jnl`	Efficient Model Development through Fine-tuning Transfer. CoRR Pin-Jie Lin, Rishab Balasubramanian, Fengyuan Liu, Nikhil Kandpal, Tu Vu
2025	J	`jnl`	Enhancing Training Data Attribution with Representational Optimization. CoRR Weiwei Sun, Haokun Liu, Nikhil Kandpal, Colin Raffel, Yiming Yang
2025	—	`conf`	Position: The Most Expensive Part of an LLM should be its Training Data. ICML (Position Papers) Nikhil Kandpal, Colin Raffel
2025	J	`jnl`	Position: The Most Expensive Part of an LLM should be its Training Data. CoRR Nikhil Kandpal, Colin Raffel
2025	J	`jnl`	The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text. CoRR Nikhil Kandpal, Brian Lester, Colin Raffel, Sebastian Majstorovic, Stella Biderman, Baber Abbasi, Luca Soldaini, Enrico Shippole, A. Feder Cooper, Aviya Skowron, John Kirchenbauer, Shayne Longpre, Lintang Sutawika, Alon Albalak, Zhenlin Xu, Guilherme Penedo, Loubna Ben Allal, Elie Bakouch, John David Pressman, Honglu Fan, Dashiell Stander, Guangyu Song, Aaron Gokaslan, Tom Goldstein, Brian R. Bartoldson, Bhavya Kailkhura, Tyler Murray
2024	J	`jnl`	AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution. CoRR Fengyuan Liu, Nikhil Kandpal, Colin Raffel
2024	A*	`conf`	User Inference Attacks on Large Language Models. EMNLP Nikhil Kandpal, Krishna Pillutla, Alina Oprea, Peter Kairouz, Christopher A. Choquette-Choo, Zheng Xu
2023	J	`jnl`	Backdoor Attacks for In-Context Learning with Language Models. CoRR Nikhil Kandpal, Matthew Jagielski, Florian Tramèr, Nicholas Carlini
2023	A*	`conf`	Git-Theta: A Git Extension for Collaborative Development of Machine Learning Models. ICML Nikhil Kandpal, Brian Lester, Mohammed Muqeeth, Anisha Mascarenhas, Monty Evans, Vishal Baskaran, Tenghao Huang, Haokun Liu, Colin Raffel
2023	J	`jnl`	Git-Theta: A Git Extension for Collaborative Development of Machine Learning Models. CoRR Nikhil Kandpal, Brian Lester, Mohammed Muqeeth, Anisha Mascarenhas, Monty Evans, Vishal Baskaran, Tenghao Huang, Haokun Liu, Colin Raffel
2023	A*	`conf`	Large Language Models Struggle to Learn Long-Tail Knowledge. ICML Nikhil Kandpal, Haikang Deng, Adam Roberts, Eric Wallace, Colin Raffel
2023	J	`jnl`	User Inference Attacks on Large Language Models. CoRR Nikhil Kandpal, Krishna Pillutla, Alina Oprea, Peter Kairouz, Christopher A. Choquette-Choo, Zheng Xu
2022	A*	`conf`	Deduplicating Training Data Mitigates Privacy Risks in Language Models. ICML Nikhil Kandpal, Eric Wallace, Colin Raffel
2022	J	`jnl`	Deduplicating Training Data Mitigates Privacy Risks in Language Models. CoRR Nikhil Kandpal, Eric Wallace, Colin Raffel
2022	J	`jnl`	Large Language Models Struggle to Learn Long-Tail Knowledge. CoRR Nikhil Kandpal, Haikang Deng, Adam Roberts, Eric Wallace, Colin Raffel
2022	Misc	`conf`	Music Enhancement via Image Translation and Vocoding. ICASSP Nikhil Kandpal, Oriol Nieto, Zeyu Jin
2022	J	`jnl`	Music Enhancement via Image Translation and Vocoding. CoRR Nikhil Kandpal, Oriol Nieto, Zeyu Jin
2019	—	`conf`	Universal Adversarial Triggers for Attacking and Analyzing NLP. EMNLP/IJCNLP (1) Eric Wallace, Shi Feng, Nikhil Kandpal, Matt Gardner, Sameer Singh
2019	J	`jnl`	Universal Adversarial Triggers for NLP. CoRR Eric Wallace, Shi Feng, Nikhil Kandpal, Matt Gardner, Sameer Singh