Kyle O'Brien
- Papers
- 4
Cite
Notes
Only stored in your browser.
4papers
Authored papers
4Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs
arXiv 2025
Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon
arXiv 2024
Composable Interventions for Language Models
arXiv 2024
Improving Black-box Robustness with In-Context Rewriting
arXiv 2024
Affiliations
No known affiliations.
Frequent co-authors
10from 4 papers
Stella Biderman
founder
Thomas Hartvigsen
Alvin Deng
Anurag Vaidya
Arinbjörn Kolbeinsson
Christopher A. Choquette-Choo
Faisal Mahmood
Geoffrey Irving
Hamid Palangi
researcher
Isha Puri