Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Nina Panickssery
Observed name:
Panickssery, Nina
Institution:
Anthropic (United States)
Observed institution:
Anthropic (United States)
OpenAlex ID:
A5114449312
Refusal in Language Models Is Mediated by a Single Direction
2024
·
Andy Arditi
, Oscar Obeso
, et al.
·
neural information processing systems
·
72
Many-shot Jailbreaking
2024
·
Cem Anil
, Esin Durmus
, et al.
·
neural information processing systems
·
26
Understanding Jailbreak Success: A Study of Latent Space Dynamics in Large Language Models
2026
·
Sarah Ball
, Frauke Kreuter
, et al.
·
Conference of the European Chapter of the Association for Computational Linguistics
·
2
PDF
Mechanistically Eliciting Latent Behaviors in Language Models
2026
·
Mack, Andrew
, Panickssery, Nina
, et al.
·
arXiv (Cornell University)
PDF
Understanding Jailbreak Success: A Study of Latent Space Dynamics in Large Language Models
2026
·
Association for Computational Linguistics 2026
, Ball, Sarah
, et al.
·
Underline Science Inc.
Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMs
2025
·
Shilov, Igor
, Cloud, Alex
, et al.
·
arXiv (Cornell University)
PDF
Mitigating Many-Shot Jailbreaking
2025
·
Ackerman, Christopher M.
, Panickssery, Nina
·
arXiv (Cornell University)
PDF
Inspection and Control of Self-Generated-Text Recognition Ability in Llama3-8b-Instruct
2024
·
Ackerman, Christopher
, Panickssery, Nina
·
arXiv (Cornell University)
PDF
Show more works
View as search
Works count:
9
Citation count:
100
H-index:
2
I10-index:
2
Year
Topic
Type
