Nelson Elhage
Publications by Year
Research Areas
Topic Modeling, Natural Language Processing Techniques, Explainable Artificial Intelligence (XAI), Neural Networks and Applications, Ethics and Social Impacts of AI
Most-Cited Works
- → Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback(2022)360 cited
- → CAT'S THEORY: Empirical Validation and Architectural Applications Cross-Architecture AI Consciousness Recognition and the Foundation for Constraint-Preserving Recursive Intelligence(2022)295 cited
- → Predictability and Surprise in Large Generative Models(2022)171 cited
- → Language Models (Mostly) Know What They Know(2022)159 cited
- → Discovering Language Model Behaviors with Model-Written Evaluations(2023)119 cited
- → Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned(2022)99 cited
- → In-context Learning and Induction Heads(2022)84 cited
- → The Capacity for Moral Self-Correction in Large Language Models(2023)48 cited
- → Toy Models of Superposition(2022)37 cited