Amanda Askell
- 3works
- 3Pith-reviewed
- 100.0%Recognition coverage
- 0queued
works
- Language Models (Mostly) Know What They Know Pith 2022 · cs.CL · verdict UNVERDICTED · 206 Pith citing
- Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned Pith 2022 · cs.CL · verdict ACCEPT · 105 Pith citing
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback Pith 2022 · cs.CL · verdict UNVERDICTED · 344 Pith citing