Saurav Kadavath

机构：UC Berkeley

发表论文 41 篇 · 总被引 21634 次 · h-index 16

代表论文

• Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback (2022 · arXiv.org · 被引 4293)
• Constitutional AI: Harmlessness from AI Feedback (2022 · arXiv.org · 被引 3506)
• Language Models (Mostly) Know What They Know (2022 · arXiv.org · 被引 1855)
• Measuring Coding Challenge Competence With APPS (2021 · NeurIPS Datasets and Benchmarks · 被引 1234)
• Discovering Language Model Behaviors with Model-Written Evaluations (2022 · Annual Meeting of the Association for Computational Linguistics · 被引 967)
• Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned (2022 · arXiv.org · 被引 859)