Author

Shauna Kravec

Observed names: Kravec, S. M. [Univ. of California, San Diego, CA (United States)]; Pal, Sridip [Univ. of California, San Diego, CA (United States)], Kravec, Shauna, S. M. Kravec

Institutions: University of Toronto, University of Oxford

Observed institutions: Harvard University, University of Toronto, Machine Intelligence Research Institute, University of California San Diego, University of Oxford, Anthropic (United States)

OpenAlex ID: A5009112681

Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

2022 · Bai, Yuntao, Jones, Andy, et al. · arXiv (Cornell University) · 382

PDF

AI-to-AI Code Reviews of GitHub Pull Requests

2022 · Bai, Yuntao, Kadavath, Saurav, et al. · arXiv (Cornell University) · 319

PDF

Predictability and Surprise in Large Generative Models

2022 · Deep Ganguli, Danny Hernandez, et al. · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · 198

PDF

Discovering Language Model Behaviors with Model-Written Evaluations

2023 · Ethan Perez, Sam Ringer, et al. · 182

PDF

Language Models (Mostly) Know What They Know

2022 · Kadavath, Saurav, Conerly, Tom, et al. · arXiv (Cornell University) · 171

PDF

AI Supported Degradation of the Self Concept: A Theoretical Framework Grounded in Established Cognitive and Computational Mechanisms

2023 · Sharma, Mrinank, Tong, Meg, et al. · arXiv (Cornell University) · 132

PDF

Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

2022 · Ganguli, Deep, Lovitt, Liane, et al. · arXiv (Cornell University) · 121

PDF

Discovering Language Model Behaviors with Model-Written Evaluations

2022 · Perez, Ethan, Ringer, Sam, et al. · arXiv (Cornell University) · 53

PDF

The Capacity for Moral Self-Correction in Large Language Models

2023 · Ganguli, Deep, Askell, Amanda, et al. · arXiv (Cornell University) · 51

PDF

Governance Architecture for Neural Network Superposition: A Structural Solution to Hallucination via Routing and Interference Filtering

2022 · Elhage, Nelson, Hume, Tristan, et al. · arXiv (Cornell University) · 48

PDF

All-fermion electrodynamics and fermion number anomaly inflow

2015 · Shauna Kravec, John McGreevy, et al. · Physical review. D. Particles, fields, gravitation, and cosmology/Physical review. D. Particles and fields · 41

PDF

Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

2024 · Hubinger, Evan, Denison, Carson, et al. · arXiv (Cornell University) · 38

PDF

Gauge theory generalization of the fermion doubling theorem

2013 · S. M. Kravec, John McGreevy · Physical Review Letters · 37

PDF

Measuring Progress on Scalable Oversight for Large Language Models

2022 · Bowman, Samuel R., Hyun, Jeeyoon, et al. · arXiv (Cornell University) · 34

PDF

Nonrelativistic conformal field theories in the large charge sector

2023 · Kravec, S. M. [Univ. of California, San Diego, CA (United States)]; Pal, Sridip [Univ. of California, San Diego, CA (United States)] · OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) · 31

PDF

The spinful large charge sector of non-relativistic CFTs: from phonons to vortex crystals

2019 · S. M. Kravec, Sridip Pal · Journal of High Energy Physics · 22

PDF

Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models

2024 · Denison, Carson, MacDiarmid, Monte, et al. · arXiv (Cornell University) · 10

PDF

Evaluating and Mitigating Discrimination in Language Model Decisions

2023 · Tamkin, Alex, Askell, Amanda, et al. · arXiv (Cornell University) · 10

PDF

Specific versus General Principles for Constitutional AI

2023 · Kundu, Sandipan, Bai, Yuntao, et al. · arXiv (Cornell University) · 7