Asa Cooper Stickland
NYU postdoc/researcher working on language model alignment, evaluation, and safety; previously at Edinburgh.
- Role
- researcher
- Currently at
- New York University
- twitter.com/AsaCoopStick
- Scholar
- scholar.google.com/citations
- Papers
- 5
Cite
Notes
Only stored in your browser.
5papers
Authored papers
5Async Control: Stress-testing Asynchronous Control Measures for LLM Agents
arXiv 2025
Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs
arXiv 2024
Does Unlearning Truly Unlearn? A Black Box Evaluation of LLM Unlearning Methods
arXiv 2024
GPQA: A Graduate-Level Google-Proof Q&A Benchmark
COLM
The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"
arXiv 2023
Affiliations
Frequent co-authors
10from 5 papers