Catherine Olsson

Computer Science · Physical Sciences

22h-index3.1kcitations42works5.02yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Topic Modeling(7), Natural Language Processing Techniques(7), Explainable Artificial Intelligence (XAI)(6), Assistive Technology in Communication and Mobility(5), Visual perception and processing mechanisms(4)

Publications42 total

Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming
arXiv (Cornell University)·2025· 5 citedOpen Access
Normalization by orientation-tuned surround in human V1-V3
PLoS Computational Biology·2023· 4 citedOpen Access
Issue Information
Australian and New Zealand Journal of Family Therapy·2023Open Access
Specific versus General Principles for Constitutional AI
arXiv (Cornell University)·2023· 7 citedOpen Access
The Capacity for Moral Self-Correction in Large Language Models
arXiv (Cornell University)·2023· 48 citedOpen Access
Discovering Language Model Behaviors with Model-Written Evaluations
2023· 114 citedOpen Access
Discovering Language Model Behaviors with Model-Written Evaluations
arXiv (Cornell University)·2022· 39 citedOpen Access
CAT'S THEORY: Empirical Validation and Architectural Applications Cross-Architecture AI Consciousness Recognition and the Foundation for Constraint-Preserving Recursive Intelligence
arXiv (Cornell University)·2022· 289 citedOpen Access
In-context Learning and Induction Heads
arXiv (Cornell University)·2022· 83 citedOpen Access
Toy Models of Superposition
arXiv (Cornell University)·2022· 37 citedOpen Access
Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned
arXiv (Cornell University)·2022· 98 citedOpen Access
Language Models (Mostly) Know What They Know
arXiv (Cornell University)·2022· 158 citedOpen Access
Predictability and Surprise in Large Generative Models
2022 ACM Conference on Fairness, Accountability, and Transparency·2022· 164 citedOpen Access
Scaling Laws and Interpretability of Learning from Repeated Data
arXiv (Cornell University)·2022· 22 citedOpen Access
Cohort Profile: The Australian Temperament Project Generation 3 Study: A population-based multigenerational prospective cohort study of socio-emotional health and development
2022Open Access
Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
arXiv (Cornell University)·2022· 359 citedOpen Access
Predictability and Surprise in Large Generative Models
arXiv (Cornell University)·2022· 21 citedOpen Access
A General Language Assistant as a Laboratory for Alignment
arXiv (Cornell University)·2021· 27 citedOpen Access
Normalization by orientation-tuned surround in human V1-V3
2021Open Access
Dota 2 with Large Scale Deep Reinforcement Learning
arXiv (Cornell University)·2019· 1.0k citedOpen Access
page 1 of 3Next →

Frequent Co-authors

Jared Kaplan(15), Tom Henighan(14), Nelson Elhage(14), Sam McCandlish(14), Amanda Askell(13), Dawn Drain(13), Dario Amodei(13), Yuntao Bai(12), Kamal Ndousse(12), Anna Chen(12), Zac Hatfield-Dodds(12), Deep Ganguli(11), Nicholas Joseph(11), Scott G. Johnston(11), Shauna Kravec(11), Tom Brown(11), Ben Mann(11), Andy Jones(9), Saurav Kadavath(8), Jack A. Clark(8)