Nova Dassarma
Artificial Intelligence · 2021–2024
A researcher in the Science corpus: 12 papers; trusts 4 researchers and is trusted by 0 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 413 citations into it
Whom Nova Dassarma trusts
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton (in Artificial Intelligence)
- Yoshua Bengio (in Artificial Intelligence)
- Ilya Sutskever (in Artificial Intelligence)
- Diederik P. Kingma (in Artificial Intelligence)
Papers from Nova Dassarma's perspective
Ordered by how strongly the researchers Nova Dassarma trusts endorse each paper. Same corpus, a different order for every researcher.
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet classification with deep convolutional neural networks
- Language Models are Few-Shot Learners (Neural Information Processing Systems)
- Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer (Journal of machine learning research)
- Improving Language Understanding by Generative Pre-Training
- Intriguing properties of neural networks
- Learning Transferable Visual Models From Natural Language Supervision (International Conference on Machine Learning)
- Scaling Laws for Neural Language Models (arXiv.org)
- Model Cards for Model Reporting
- Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks
Their papers
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback (2022) — 4,254 citations
- A General Language Assistant as a Laboratory for Alignment (2021) — 1,175 citations
- Constitutional AI: Harmlessness from AI Feedback (2022) — 3,377 citations
- Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned (2022) — 837 citations
- Language Models (Mostly) Know What They Know (2022) — 1,782 citations
- Predictability and Surprise in Large Generative Models (2022) — 365 citations
- In-context Learning and Induction Heads (2022) — 942 citations
- The Capacity for Moral Self-Correction in Large Language Models (2023) — 214 citations
- Discovering Language Model Behaviors with Model-Written Evaluations (2022) — 917 citations
- Scaling Laws and Interpretability of Learning from Repeated Data (2022) — 166 citations
- Measuring Progress on Scalable Oversight for Large Language Models (2022) — 226 citations
- Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training (2024) — 489 citations