Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Luxi He
Observed name:
He, Luxi
Institution:
Princeton University
Observed institution:
Princeton University
OpenAlex ID:
A5109737166
SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal
2024
·
Xie, Tinghao
, Qi, Xiangyu
, et al.
·
arXiv (Cornell University)
·
7
PDF
Fantastic Copyrighted Beasts and How (Not) to Generate Them
2024
·
He, Luxi
, Huang, Yangsibo
, et al.
·
arXiv (Cornell University)
·
3
PDF
AI Risk Management Should Incorporate Both Safety and Security
2024
·
Qi, Xiangyu
, Huang, Yangsibo
, et al.
·
arXiv (Cornell University)
·
3
PDF
What is in Your Safe Data? Identifying Benign Data that Breaks Safety
2024
·
He, Luxi
, Xia, Mengzhou
, et al.
·
arXiv (Cornell University)
·
1
PDF
Statutory construction and interpretation for AI
2026
·
Luxi He
, Nimra Nadeem
, et al.
·
Proceedings of the National Academy of Sciences
PDF
The Model Hears You: Audio Language Model Deployments Should Consider the Principle of Least Privilege
2025
·
Luxi He
, Xiangyu Qi
, et al.
·
Proceedings of the AAAI/ACM Conference on AI Ethics and Society
PDF
On Evaluating the Durability of Safeguards for Open-Weight LLMs
2024
·
Qi, Xiangyu
, Wei, Boyi
, et al.
·
arXiv (Cornell University)
PDF
Show more works
View as search
Works count:
7
Citation count:
14
H-index:
3
I10-index:
Year
Topic
Type
