Yangsibo Huang
- Papers
- 4
Cite
Notes
Only stored in your browser.
4papers
Authored papers
4SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal Behaviors
arXiv 2024
Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models
arXiv 2024
On Evaluating the Durability of Safeguards for Open-Weight LLMs
arXiv 2024
Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation
arXiv 2023
Affiliations
No known affiliations.
Frequent co-authors
10from 4 papers