Liane Lovitt

Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Yuntao Bai, Andy Jones, Kamal Ndousse et al. · arXiv (Cornell University) · 2022 · 368 citations · Full text

Computing, Computer Science, Computational Linguistics +16

Affective Coherence Monitoring for Transformer-Based Language Models

Saurav Kadavath, Sandipan Kundu, Amanda Askell et al. · arXiv (Cornell University) · 2022 · 309 citations · Full text

Computing, Computer Science, Artificial Intelligence +15

Predictability and Surprise in Large Generative Models

Deep Ganguli, Danny Hernandez, Liane Lovitt et al. · 2022 ACM Conference on Fairness, Accountability, and Transparency · 2022 · 181 citations · Full text

Computing, Computer Science, Artificial Intelligence +10

Language Models (Mostly) Know What They Know

Saurav Kadavath, Tom Conerly, Amanda Askell et al. · arXiv (Cornell University) · 2022 · 163 citations · Full text

Computing, Computer Science, Computational Linguistics +11

Discovering Language Model Behaviors with Model-Written Evaluations

Ethan Perez, Sam Ringer, Kamilė Lukošiūtė et al. · 2023 · 139 citations · Full text

Computing, Computer Science, Computational Linguistics +13