Kai Li

Full Professor, Computer Science, Princeton University

Joined

July 2019

Names

Kai Li

Emails

****@cs.princeton.edu (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

Full Professor

Computer Science, Princeton University (princeton.edu)

1995 – Present

Associate Professor

Princeton University (princeton.edu)

1992 – 1995

Assistant Professor

Princeton University (princeton.edu)

1986 – 1992

Advisors, Relations & Conflicts

No relations added

Expertise

No areas of expertise listed

Publications

Learned Prefix Caching for Efficient LLM Inference
Dongsheng Yang, Austin Li, Kai Li, Wyatt Lloyd
- NeurIPS 2025 poster
- Readers: Everyone
SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal
Tinghao Xie, Xiangyu Qi, Yi Zeng, Yangsibo Huang, Udari Madhushani Sehwag, Kaixuan Huang, Luxi He, Boyi Wei, Dacheng Li, Ying Sheng, Ruoxi Jia, Bo Li, Kai Li, Danqi Chen, Peter Henderson, Prateek Mittal
- ICLR 2025 Poster
- Readers: Everyone
Evaluating Copyright Takedown Methods for Language Models
Boyi Wei, Weijia Shi, Yangsibo Huang, Noah A. Smith, Chiyuan Zhang, Luke Zettlemoyer, Kai Li, Peter Henderson
- NeurIPS 2024 Track Datasets and Benchmarks Poster
- Readers: Everyone
SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal Behaviors
Tinghao Xie, Xiangyu Qi, Yi Zeng, Yangsibo Huang, Udari Madhushani Sehwag, Boyi Wei, Luxi He, Kaixuan Huang, Dacheng Li, Ying Sheng, Ruoxi Jia, Bo Li, Danqi Chen, Kai Li, Peter Henderson, Prateek Mittal
- Submitted to NeurIPS 2024 Track Datasets and Benchmarks
- Readers: Everyone
BitDelta: Your Fine-Tune May Only Be Worth One Bit
James Liu, Guangxuan Xiao, Kai Li, Jason D. Lee, Song Han, Tri Dao, Tianle Cai
- NeurIPS 2024 poster
- Readers: Everyone
Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation
Yangsibo Huang, Samyak Gupta, Mengzhou Xia, Kai Li, Danqi Chen
- ICLR 2024 spotlight
- Readers: Everyone
Is EMA Robust? Examining the Robustness of Data Auditing and a Novel Non-calibration Extension
Ayush Alag, Yangsibo Huang, Kai Li
- RegML 2023
- Readers: Everyone
Privacy Implications of Retrieval-Based Language Models
Yangsibo Huang, Samyak Gupta, Zexuan Zhong, Kai Li, Danqi Chen
- EMNLP 2023 Main
- Readers: Everyone
A Dataset Auditing Method for Collaboratively Trained Machine Learning Models
Yangsibo Huang, Chun-Yin Huang, Xiaoxiao Li, Kai Li
- 16 May 2023
- OpenReview Archive Direct Upload
- Readers: Everyone
Recovering Private Text in Federated Learning of Language Models
Samyak Gupta, Yangsibo Huang, Zexuan Zhong, Tianyu Gao, Kai Li, Danqi Chen
- Published: 31 Oct 2022, Last Modified: 08 Feb 2026
- NeurIPS 2022 Accept
- Readers: Everyone

View all 149 publications

Co-Authors

View all 180 co-authors