Nicholas Joseph

发表论文 26 篇 · 总被引 25080 次 · h-index 18

代表论文

• Evaluating Large Language Models Trained on Code (2021 · arXiv.org · 被引 11018)
• Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback (2022 · arXiv.org · 被引 4303)
• Constitutional AI: Harmlessness from AI Feedback (2022 · arXiv.org · 被引 3538)
• Language Models (Mostly) Know What They Know (2022 · arXiv.org · 被引 1877)
• A General Language Assistant as a Laboratory for Alignment (2021 · arXiv.org · 被引 1196)
• In-context Learning and Induction Heads (2022 · arXiv.org · 被引 981)