Dawn Drain

Computer Science · Physical Sciences

19h-index2.6kcitations31works0.02yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

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

Research Topics

Topic Modeling(17), Software Engineering Research(14), Natural Language Processing Techniques(13), Software Testing and Debugging Techniques(8), Explainable Artificial Intelligence (XAI)(5)

Publications31 total

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
Exploring and evaluating personalized models for code generation
Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering·2022· 10 citedOpen Access
Measuring Progress on Scalable Oversight for Large Language Models
arXiv (Cornell University)·2022· 31 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
Generating accurate assert statements for unit test cases using pretrained transformers
2022· 85 citedOpen 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
Long-Range Modeling of Source Code Files with eWASH: Extended Window Access by Syntax Hierarchy
arXiv (Cornell University)·2021Open Access
Long-Range Modeling of Source Code Files with eWASH: Extended Window\n Access by Syntax Hierarchy
arXiv (Cornell University)·2021· 1 citedOpen Access
Distilling Transformers for Neural Cross-Domain Search
arXiv (Cornell University)·2021· 1 citedOpen Access
Generating bug-fixes using pretrained transformers
2021· 6 citedOpen Access
page 1 of 2Next →

Frequent Co-authors

Neel Sundaresan(16), Tom Henighan(14), Nelson Elhage(14), Dario Amodei(14), Sam McCandlish(14), Jared Kaplan(14), A. Svyatkovskiy(13), Catherine Olsson(13), Colin B. Clement(12), Yuntao Bai(12), Kamal Ndousse(12), Amanda Askell(12), Anna Chen(12), Zac Hatfield-Dodds(12), Scott G. Johnston(12), Tom Brown(12), Ben Mann(12), Deep Ganguli(11), Nicholas Joseph(11), Shauna Kravec(11)